Xiang Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiang Wu has a total of 129 co-authors. Here are the top co-authors by number of shared publications:
- Khin Wee Lai
Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
14 shared publications Huanhuan Wang
9 shared publications- Huanhuan Wang
Institute of Medical Information Security, Xuzhou Medical University, Xuzhou, China
9 shared publications - Khairunnisa Hasikin
Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
7 shared publications - Samiappan Dhanalakshmi
SRM Institute of Science and Technology
5 shared publications - Yongting Zhang
Institute of Medical Information Security, Xuzhou Medical University, Xuzhou, China
5 shared publications
Latest Publications
- Open Access
- 9 July 2026
- Published by Elsevier in Complementary Therapies in Medicine
- Vol. 101, 103405
Effects of Automated Massage Chair Therapy on Mental Health and Physical Health: A Comprehensive Study
- 9 July 2026
- Published by Elsevier in Complementary Therapies in Medicine
- Vol. 101, 103405
Open AccessEffects of Automated Massage Chair Therapy on Mental Health and Physical Health: A Comprehensive Study
- Top Cited PapersOpen Access
- 30 March 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e83743
A Bilayer Feature Fusion Framework for Pan-Cancer Survival Prediction Based on Multihead Attention and Adaptive Differential Privacy: Model Development and Validation Study
Background: In the field of precision medicine, pan-cancer survival prediction is crucial for individualized oncology diagnosis and treatment. Although multimodal data fusion techniques have significantly improved prediction accuracy, existing studies generally overlook the sensitivity of medical data and the need for privacy protection. Objective: To address the aforementioned problem, this study aims to propose a bilayer feature fusion framework based on the multihead attention mechanism and adaptive differential privacy, which balances precise feature extraction and sensitive data protection. Methods: Specifically, the multihead attention mechanism was integrated into bilayer feature extraction and fusion. Layer-wise relevance analysis was used to calculate the correlation between features and outcomes, and Laplacian noise was adaptively added based on the calculation results to achieve collaborative optimization of precise feature extraction and sensitive data protection. Additionally, the concordance index (C-index) and 5-fold cross-validation were used to compare the proposed method with state-of-the-art approaches. Results: The proposed model achieved superior performance in both pan-cancer and single-cancer survival prediction, validated via the C-index and 5-fold cross-validation. In pan-cancer scenarios, the trimodal combination of clinical data, messenger RNA data, and microRNA expression data achieved the highest C-index of 0.799, outperforming multiple existing multimodal survival prediction approaches. After adaptive Laplacian noise injection for privacy protection, the model’s accuracy decreased by only 0.01-0.03 while satisfying ϵ-differential privacy. For single-cancer prediction, the proposed method achieved higher C-index values in 18 out of 20 cancer types compared with representative deep learning–based survival models, with 7 types showing significant improvements (C-index difference >0.1) and more stable performance distributions. Furthermore, pan-cancer–trained models generally outperformed single-cancer–trained counterparts in most cancer types, highlighting the value of shared predictive features across cancers. Conclusions: This study provides a solution that balances prediction accuracy and privacy security for pan-cancer survival prediction, laying the foundation for the efficient use of medical data under privacy protection. Future work may further integrate pathological images and proteomics data to expand the model’s applications in cancer subtype classification and biomarker discovery.
- 30 March 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14, e83743
Top Cited PapersOpen AccessA Bilayer Feature Fusion Framework for Pan-Cancer Survival Prediction Based on Multihead Attention and Adaptive Differential Privacy: Model Development and Validation Study
Background: In the field of precision medicine, pan-cancer survival prediction is crucial for individualized oncology diagnosis and treatment. Although multimodal data fusion techniques have significantly improved prediction accuracy, existing studies generally overlook the sensitivity of medical data and the need for privacy protection. Objective: To address the aforementioned problem, this study aims to propose a bilayer feature fusion framework based on the multihead attention mechanism and adaptive differential privacy, which balances precise feature extraction and sensitive data protection. Methods: Specifically, the multihead attention mechanism was integrated into bilayer feature extraction and fusion. Layer-wise relevance analysis was used to calculate the correlation between features and outcomes, and Laplacian noise was adaptively added based on the calculation results to achieve collaborative optimization of precise feature extraction and sensitive data protection. Additionally, the concordance index (C-index) and 5-fold cross-validation were used to compare the proposed method with state-of-the-art approaches. Results: The proposed model achieved superior performance in both pan-cancer and single-cancer survival prediction, validated via the C-index and 5-fold cross-validation. In pan-cancer scenarios, the trimodal combination of clinical data, messenger RNA data, and microRNA expression data achieved the highest C-index of 0.799, outperforming multiple existing multimodal survival prediction approaches. After adaptive Laplacian noise injection for privacy protection, the model’s accuracy decreased by only 0.01-0.03 while satisfying ϵ-differential privacy. For single-cancer prediction, the proposed method achieved higher C-index values in 18 out of 20 cancer types compared with representative deep learning–based survival models, with 7 types showing significant improvements (C-index difference >0.1) and more stable performance distributions. Furthermore, pan-cancer–trained models generally outperformed single-cancer–trained counterparts in most cancer types, highlighting the value of shared predictive features across cancers. Conclusions: This study provides a solution that balances prediction accuracy and privacy security for pan-cancer survival prediction, laying the foundation for the efficient use of medical data under privacy protection. Future work may further integrate pathological images and proteomics data to expand the model’s applications in cancer subtype classification and biomarker discovery.
- Open Access
- 8 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
A Bilayer Feature Fusion Framework for Pan-Cancer Survival Prediction Based on Multihead Attention and Adaptive Differential Privacy: Model Development and Validation Study (Preprint)
BACKGROUND In the field of precision medicine, pan-cancer survival prediction is crucial for individualized oncology diagnosis and treatment. Although multimodal data fusion techniques have significantly improved prediction accuracy, existing studies generally overlook the sensitivity of medical data and the need for privacy protection. OBJECTIVE To address the aforementioned problem, this study aims to propose a bilayer feature fusion framework based on the multihead attention mechanism and adaptive differential privacy, which balances precise feature extraction and sensitive data protection. METHODS Specifically, the multihead attention mechanism was integrated into bilayer feature extraction and fusion. Layer-wise relevance analysis was used to calculate the correlation between features and outcomes, and Laplacian noise was adaptively added based on the calculation results to achieve collaborative optimization of precise feature extraction and sensitive data protection. Additionally, the concordance index (C-index) and 5-fold cross-validation were used to compare the proposed method with state-of-the-art approaches. RESULTS The proposed model achieved superior performance in both pan-cancer and single-cancer survival prediction, validated via the C-index and 5-fold cross-validation. In pan-cancer scenarios, the trimodal combination of clinical data, messenger RNA data, and microRNA expression data achieved the highest C-index of 0.799, outperforming multiple existing multimodal survival prediction approaches. After adaptive Laplacian noise injection for privacy protection, the model’s accuracy decreased by only 0.01-0.03 while satisfying ϵ-differential privacy. For single-cancer prediction, the proposed method achieved higher C-index values in 18 out of 20 cancer types compared with representative deep learning–based survival models, with 7 types showing significant improvements (C-index difference >0.1) and more stable performance distributions. Furthermore, pan-cancer–trained models generally outperformed single-cancer–trained counterparts in most cancer types, highlighting the value of shared predictive features across cancers. CONCLUSIONS This study provides a solution that balances prediction accuracy and privacy security for pan-cancer survival prediction, laying the foundation for the efficient use of medical data under privacy protection. Future work may further integrate pathological images and proteomics data to expand the model’s applications in cancer subtype classification and biomarker discovery.
- 8 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessA Bilayer Feature Fusion Framework for Pan-Cancer Survival Prediction Based on Multihead Attention and Adaptive Differential Privacy: Model Development and Validation Study (Preprint)
BACKGROUND In the field of precision medicine, pan-cancer survival prediction is crucial for individualized oncology diagnosis and treatment. Although multimodal data fusion techniques have significantly improved prediction accuracy, existing studies generally overlook the sensitivity of medical data and the need for privacy protection. OBJECTIVE To address the aforementioned problem, this study aims to propose a bilayer feature fusion framework based on the multihead attention mechanism and adaptive differential privacy, which balances precise feature extraction and sensitive data protection. METHODS Specifically, the multihead attention mechanism was integrated into bilayer feature extraction and fusion. Layer-wise relevance analysis was used to calculate the correlation between features and outcomes, and Laplacian noise was adaptively added based on the calculation results to achieve collaborative optimization of precise feature extraction and sensitive data protection. Additionally, the concordance index (C-index) and 5-fold cross-validation were used to compare the proposed method with state-of-the-art approaches. RESULTS The proposed model achieved superior performance in both pan-cancer and single-cancer survival prediction, validated via the C-index and 5-fold cross-validation. In pan-cancer scenarios, the trimodal combination of clinical data, messenger RNA data, and microRNA expression data achieved the highest C-index of 0.799, outperforming multiple existing multimodal survival prediction approaches. After adaptive Laplacian noise injection for privacy protection, the model’s accuracy decreased by only 0.01-0.03 while satisfying ϵ-differential privacy. For single-cancer prediction, the proposed method achieved higher C-index values in 18 out of 20 cancer types compared with representative deep learning–based survival models, with 7 types showing significant improvements (C-index difference >0.1) and more stable performance distributions. Furthermore, pan-cancer–trained models generally outperformed single-cancer–trained counterparts in most cancer types, highlighting the value of shared predictive features across cancers. CONCLUSIONS This study provides a solution that balances prediction accuracy and privacy security for pan-cancer survival prediction, laying the foundation for the efficient use of medical data under privacy protection. Future work may further integrate pathological images and proteomics data to expand the model’s applications in cancer subtype classification and biomarker discovery.
- Top Cited Papers
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 43 (6) , 2266-2278
Dynamic Security Computing Framework With Zero Trust Based on Privacy Domain Prevention and Control Theory
With a growing security threat in wireless communication networks, a promising method for secure next-generation networks is a zero-trust framework focusing on authentication schemes. How to analyze the risks involved in authentication is a challenge. This study quantifies authentication risks within the zero-trust framework and introduces a privacy domain prevention-control theory. The theory encompasses dynamic privacy risk assessment, intelligent risk classification, and automated selection of privacy protection schemes. First, a dynamic privacy risk assessment method, based on physical entity relationships, is proposed to evaluate all privacy risks. Second, a five-category risk classification method is designed to categorize privacy risks, facilitating the selection of prevention-control schemes, with its rationality mathematically validated. Additionally, an Analytical Hierarchy Process (AHP)-based method is introduced to guide the optimal selection of prevention-control schemes for various scenarios. Finally, the practical application of the theory in medicine multi-modal computing scene of wireless body area networks demonstrates its effectiveness. The experimental results also show the superiority and feasibility of the proposed methods.
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 43 (6) , 2266-2278
Top Cited PapersDynamic Security Computing Framework With Zero Trust Based on Privacy Domain Prevention and Control Theory
With a growing security threat in wireless communication networks, a promising method for secure next-generation networks is a zero-trust framework focusing on authentication schemes. How to analyze the risks involved in authentication is a challenge. This study quantifies authentication risks within the zero-trust framework and introduces a privacy domain prevention-control theory. The theory encompasses dynamic privacy risk assessment, intelligent risk classification, and automated selection of privacy protection schemes. First, a dynamic privacy risk assessment method, based on physical entity relationships, is proposed to evaluate all privacy risks. Second, a five-category risk classification method is designed to categorize privacy risks, facilitating the selection of prevention-control schemes, with its rationality mathematically validated. Additionally, an Analytical Hierarchy Process (AHP)-based method is introduced to guide the optimal selection of prevention-control schemes for various scenarios. Finally, the practical application of the theory in medicine multi-modal computing scene of wireless body area networks demonstrates its effectiveness. The experimental results also show the superiority and feasibility of the proposed methods.
- Open Access
- 11 November 2024
- Published by Wiley in Nursing Open
- Vol. 11 (11) , e70070
Development of a Frailty Prediction Model Among Older Adults in China: A Cross‐Sectional Analysis Using the Chinese Longitudinal Healthy Longevity Survey
Aims: To identify the risk factors associated with frailty among older adults in China and develop a predictive model for assessing their frailty risk.Design: Secondary cross‐sectional analysis.Methods: The 2018 Chinese Longitudinal Healthy Longevity Survey (CLHLS) provided data for this study. A total of 9006 participants were included in the analysis. Their general demographic, socioeconomic status and health behaviour risk factors were collected in the CLHLS. Frailty was assessed using the Frailty Index. A visual nomogram model was constructed based on independent predictors identified using multivariate analysis. The nomogram's discrimination and calibration capabilities were evaluated using the C‐statistics and calibration curves. A 1000‐times resampling enhanced bootstrap method was performed for internal validation of the nomogram.Results: The results showed that living in rural settings, having a primary education level, having a spouse, having basic living security, smoking, drinking, exercising and social activities were protective factors against frailty. Increasing age, being underweight or obese, adverse self‐assessed economic status and poor sleep quality were risk factors of frailty. The AUC values of the internal validation set were 0.830. The calibration curve was close to ideal. The Brier score was 0.122. The above results showed that the nomogram model had a good predictive performance.Conclusions: A simple and fast frailty risk prediction model was developed in this study to help healthcare professionals screen older adults at high risk of frailty in China.Impact: The frailty risk prediction model will assist healthcare professionals in risk management and decision‐making and provide targeted frailty prevention interventions. Screening high‐risk older adults and early intervention can reduce the risk of adverse outcomes and save medical expenses for older adults and society, thereby realising cost‐effective planning of health resources and healthy ageing.Patient or Public Contribution: No patient or public contribution. This study was a cross‐sectional, secondary analysis of the CLHLS data.
- 11 November 2024
- Published by Wiley in Nursing Open
- Vol. 11 (11) , e70070
Open AccessDevelopment of a Frailty Prediction Model Among Older Adults in China: A Cross‐Sectional Analysis Using the Chinese Longitudinal Healthy Longevity Survey
Aims: To identify the risk factors associated with frailty among older adults in China and develop a predictive model for assessing their frailty risk.Design: Secondary cross‐sectional analysis.Methods: The 2018 Chinese Longitudinal Healthy Longevity Survey (CLHLS) provided data for this study. A total of 9006 participants were included in the analysis. Their general demographic, socioeconomic status and health behaviour risk factors were collected in the CLHLS. Frailty was assessed using the Frailty Index. A visual nomogram model was constructed based on independent predictors identified using multivariate analysis. The nomogram's discrimination and calibration capabilities were evaluated using the C‐statistics and calibration curves. A 1000‐times resampling enhanced bootstrap method was performed for internal validation of the nomogram.Results: The results showed that living in rural settings, having a primary education level, having a spouse, having basic living security, smoking, drinking, exercising and social activities were protective factors against frailty. Increasing age, being underweight or obese, adverse self‐assessed economic status and poor sleep quality were risk factors of frailty. The AUC values of the internal validation set were 0.830. The calibration curve was close to ideal. The Brier score was 0.122. The above results showed that the nomogram model had a good predictive performance.Conclusions: A simple and fast frailty risk prediction model was developed in this study to help healthcare professionals screen older adults at high risk of frailty in China.Impact: The frailty risk prediction model will assist healthcare professionals in risk management and decision‐making and provide targeted frailty prevention interventions. Screening high‐risk older adults and early intervention can reduce the risk of adverse outcomes and save medical expenses for older adults and society, thereby realising cost‐effective planning of health resources and healthy ageing.Patient or Public Contribution: No patient or public contribution. This study was a cross‐sectional, secondary analysis of the CLHLS data.
- Open Access
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 146698-146717
Knee Osteoarthritis Diagnosis With Unimodal and Multi-Modal Neural Networks: Data From the Osteoarthritis Initiative
Knee osteoarthritis (OA) is a prevalent musculoskeletal condition affecting millions worldwide, posing significant health and economic burdens. Characterized by the degeneration of joint cartilage, the progression of knee OA varies significantly among individuals, making its prediction a complex issue. Previous studies on automated knee OA diagnosis have primarily relied on unimodal data, often overlooking the valuable information present in multi-modal data. Multi-modal learning, which integrates information from various modalities, is increasingly recognized for its potential to enhance diagnostic performance in medical applications. However, such models incur a higher computational load due to the additional data required. This research investigates the feasibility of multi-modal neural networks in knee OA diagnosis by integrating structural demographic data with unstructured imaging data. Three deep learning unimodal models (InceptionV3, DIKO, and EfficientNetV2) were transformed into multi-modal architectures (MF_InceptionNet, MF_DIKO, and MF_Eff) to compare their diagnostic capabilities. The proposed multi-modal models share a common architecture, with unimodal models acting as image feature extraction backbones and separate embedding layers for demographic data. The image features and demographic embeddings are combined into a unified vector before classification. Extensive experiments were conducted to evaluate the performance of these models across different class categories and dataset sizes. MF_DIKO and InceptionV3 emerged as the best multi-modal and unimodal neural networks, respectively, with overall accuracies of 0.67 and 0.75 for 3-class severity classification. Contrary to existing literature, our findings reveal that unimodal neural networks using only imaging features outperform multi-modal networks, suggesting unimodal models might suffice in certain applications.
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 146698-146717
Open AccessKnee Osteoarthritis Diagnosis With Unimodal and Multi-Modal Neural Networks: Data From the Osteoarthritis Initiative
Knee osteoarthritis (OA) is a prevalent musculoskeletal condition affecting millions worldwide, posing significant health and economic burdens. Characterized by the degeneration of joint cartilage, the progression of knee OA varies significantly among individuals, making its prediction a complex issue. Previous studies on automated knee OA diagnosis have primarily relied on unimodal data, often overlooking the valuable information present in multi-modal data. Multi-modal learning, which integrates information from various modalities, is increasingly recognized for its potential to enhance diagnostic performance in medical applications. However, such models incur a higher computational load due to the additional data required. This research investigates the feasibility of multi-modal neural networks in knee OA diagnosis by integrating structural demographic data with unstructured imaging data. Three deep learning unimodal models (InceptionV3, DIKO, and EfficientNetV2) were transformed into multi-modal architectures (MF_InceptionNet, MF_DIKO, and MF_Eff) to compare their diagnostic capabilities. The proposed multi-modal models share a common architecture, with unimodal models acting as image feature extraction backbones and separate embedding layers for demographic data. The image features and demographic embeddings are combined into a unified vector before classification. Extensive experiments were conducted to evaluate the performance of these models across different class categories and dataset sizes. MF_DIKO and InceptionV3 emerged as the best multi-modal and unimodal neural networks, respectively, with overall accuracies of 0.67 and 0.75 for 3-class severity classification. Contrary to existing literature, our findings reveal that unimodal neural networks using only imaging features outperform multi-modal networks, suggesting unimodal models might suffice in certain applications.
- Open Access
- 27 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 145159-145173
A Privacy-Preserving Approach Using Deep Learning Models for Diabetic Retinopathy Diagnosis
Diabetes Retinopathy (DR) is the most common complication of Diabetes Mellitus and can lead to blindness if not detected early. Since DR is often asymptomatic in its early stage, timely diagnosis is crucial. Artificial Intelligence (AI) has the potential to facilitate early disease detection and treatment, but its implementation in the medical field raises significant privacy concerns. The sensitive nature of healthcare data, which includes personal information and medical history, makes data privacy a critical issue. This paper explores the implementation of AI models to predict DR risks while incorporating common defense algorithms to enhance data privacy. An unstructured dataset, specifically the DDR dataset, was used to train Deep Learning (DL) models. Two families of DL models, ResNets and DenseNets, were trained and evaluated based on the performance metrics. ResNet 50 and DenseNet 169 demonstrated superior performance and were selected for further privacy enhancement using encryption. The results indicated that privacy-preserving methods, particularly encryption, did not significantly impact the model performance. In summary, this paper highlights the potential of privacy-preserving AI in predicting the risks of DR.
- 27 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 145159-145173
Open AccessA Privacy-Preserving Approach Using Deep Learning Models for Diabetic Retinopathy Diagnosis
Diabetes Retinopathy (DR) is the most common complication of Diabetes Mellitus and can lead to blindness if not detected early. Since DR is often asymptomatic in its early stage, timely diagnosis is crucial. Artificial Intelligence (AI) has the potential to facilitate early disease detection and treatment, but its implementation in the medical field raises significant privacy concerns. The sensitive nature of healthcare data, which includes personal information and medical history, makes data privacy a critical issue. This paper explores the implementation of AI models to predict DR risks while incorporating common defense algorithms to enhance data privacy. An unstructured dataset, specifically the DDR dataset, was used to train Deep Learning (DL) models. Two families of DL models, ResNets and DenseNets, were trained and evaluated based on the performance metrics. ResNet 50 and DenseNet 169 demonstrated superior performance and were selected for further privacy enhancement using encryption. The results indicated that privacy-preserving methods, particularly encryption, did not significantly impact the model performance. In summary, this paper highlights the potential of privacy-preserving AI in predicting the risks of DR.
- Open Access
- 4 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 123757-123770
An Efficient Neural Network for Segmenting Multiple Joint Tissues From Knee MRI With Hyperparameter Optimization: Data From the Osteoarthritis Initiative
Early detection of knee osteoarthritis is crucial because the damage in the knee joint is irreversible at the advanced stage. Medical images such as Magnetic Resonance Imaging plays an important role in knee osteoarthritis diagnosis as it provides excellent visualization of the osteoarthritis imaging biomarkers. Current clinical practice relies on manual inspection of the images which is very tedious, especially for 3D volumetric data. The overall aim of the study is to develop an efficient fully automated 3D segmentation model for segmenting multiple knee joint tissues from 3D Magnetic Resonance Imaging volumes. This study contributes by implementing hyperparameter optimization techniques to develop the optimal model for knee segmentation which will be beneficial for the detection of knee osteoarthritis. The model employs depthwise separable convolution for better computational efficiency. This paper presents an efficient model for knee bones and cartilages segmentation, modelled by Tree-of-Parzen-Estimators algorithm, which achieved an average dice score of 0.939 and a Jaccard index of 0.891. Our model outperformed 3D U-Net and 3D V-Net by approximately 7% and 6% respectively in terms of Dice Similarity Coefficient, with remarkably less computations, using the same dataset. The efficient model enhances the segmentation of the knee structures for better visualization, which contributes to a more accurate diagnosis in clinical practice. It also reduces the computational cost, allowing more possible adaptation of 3D neural networks in real-world clinical settings. Therefore, this work contributes to advance medical imaging and diagnostics while also holds the potential to improve clinical practice.
- 4 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 123757-123770
Open AccessAn Efficient Neural Network for Segmenting Multiple Joint Tissues From Knee MRI With Hyperparameter Optimization: Data From the Osteoarthritis Initiative
Early detection of knee osteoarthritis is crucial because the damage in the knee joint is irreversible at the advanced stage. Medical images such as Magnetic Resonance Imaging plays an important role in knee osteoarthritis diagnosis as it provides excellent visualization of the osteoarthritis imaging biomarkers. Current clinical practice relies on manual inspection of the images which is very tedious, especially for 3D volumetric data. The overall aim of the study is to develop an efficient fully automated 3D segmentation model for segmenting multiple knee joint tissues from 3D Magnetic Resonance Imaging volumes. This study contributes by implementing hyperparameter optimization techniques to develop the optimal model for knee segmentation which will be beneficial for the detection of knee osteoarthritis. The model employs depthwise separable convolution for better computational efficiency. This paper presents an efficient model for knee bones and cartilages segmentation, modelled by Tree-of-Parzen-Estimators algorithm, which achieved an average dice score of 0.939 and a Jaccard index of 0.891. Our model outperformed 3D U-Net and 3D V-Net by approximately 7% and 6% respectively in terms of Dice Similarity Coefficient, with remarkably less computations, using the same dataset. The efficient model enhances the segmentation of the knee structures for better visualization, which contributes to a more accurate diagnosis in clinical practice. It also reduces the computational cost, allowing more possible adaptation of 3D neural networks in real-world clinical settings. Therefore, this work contributes to advance medical imaging and diagnostics while also holds the potential to improve clinical practice.
- Top Cited Papers
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (22) , 36030-36043
Augmented Intelligence of Things for Emergency Vehicle Secure Trajectory Prediction and Task Offloading
Augmented Intelligence of Things (AIoT) combines augmented intelligence algorithms with the massive data collected by IoT devices, enabling more advanced decision-making. The typical application of AIoT is Edge Computing (EC), which provides computational and storage resources at the edge to support vehicle decision-making for computation tasks. With the development of EC, task offloading has become a hopeful paradigm for assisting the time-sensitive tasks of resource-limited vehicles, such as emergency rescue vehicles, by deploying at Roadside Units (RSUs). However, the effectiveness of task offloading for emergency vehicles is hindered by the timeliness of trajectory data and the concern regarding vehicle location. Therefore, this study introduces a Secure Task Offloading scheme relying on real-time trajectory prediction, named STODRL. Firstly, this study proposes a temporal differential privacy method to disturb vehicular location information to avoid suffering from malicious stealing. Secondly, a vehicular trajectory prediction method using the Temporal Convolutional Network (TCN) is designed to improve task offloading precision by offering supplemental trajectory information. Moreover, the scheme employs a reinforcement learning method to offload computational requests effectively and avoid dimensional disasters. Simulated results validate that STODRL outperforms existing methods, significantly reducing task completion delay and ensuring the security of location information.
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (22) , 36030-36043
Top Cited PapersAugmented Intelligence of Things for Emergency Vehicle Secure Trajectory Prediction and Task Offloading
Augmented Intelligence of Things (AIoT) combines augmented intelligence algorithms with the massive data collected by IoT devices, enabling more advanced decision-making. The typical application of AIoT is Edge Computing (EC), which provides computational and storage resources at the edge to support vehicle decision-making for computation tasks. With the development of EC, task offloading has become a hopeful paradigm for assisting the time-sensitive tasks of resource-limited vehicles, such as emergency rescue vehicles, by deploying at Roadside Units (RSUs). However, the effectiveness of task offloading for emergency vehicles is hindered by the timeliness of trajectory data and the concern regarding vehicle location. Therefore, this study introduces a Secure Task Offloading scheme relying on real-time trajectory prediction, named STODRL. Firstly, this study proposes a temporal differential privacy method to disturb vehicular location information to avoid suffering from malicious stealing. Secondly, a vehicular trajectory prediction method using the Temporal Convolutional Network (TCN) is designed to improve task offloading precision by offering supplemental trajectory information. Moreover, the scheme employs a reinforcement learning method to offload computational requests effectively and avoid dimensional disasters. Simulated results validate that STODRL outperforms existing methods, significantly reducing task completion delay and ensuring the security of location information.