With the rapid advancement of Internet of Things (IoT) applications, efficient and secure communication is considered a challenging task. Symmetric authenticated key exchange (AKE) is a promising solution due to its lightweight design. However, existing studies have demonstrated that traditional symmetric AKE schemes are unable to achieve perfect forward secrecy (PFS). Although some improved schemes were proposed based on the evolution of long-term secrets, the analysis indicates that there exists a zero-sum trade-off between PFS and self-synchronization. In addition, privacy preservation remains a critical issue. In response, this paper proposes a novel three-party symmetric AKE scheme. Specifically, the secret evolving mechanism to prevent the reverse inference of crucial secret values is constructed in the scheme. Meanwhile, any reachable session state can be self-transferred to the synchronization state at the end of a complete session. The proposed scheme provides anonymity and pseudonym unlinkability to the required party, while also improving the robustness of conditional identity traceability, avoiding false accusations caused by misdirected requests. The formal analysis, heuristic analysis based on the state transition and secrecy dependency, and performance comparison indicate that the proposed scheme achieves essential properties while maintaining manageable overhead.

Utilizing the federated learning (FL) technique, data owners can collaboratively train artificial intelligence models, retaining all training data on their premises to minimize the potential for personal data breaches. However, self-interested users (e.g., free riders) bring new challenges that hinder the development of FL techniques. To this end, we propose a two-stage client selection scheme comprising a multiarmed bandit (MAB)-based candidate client selection method and an auction-based training client selection method. Specifically, our client selection scheme initially formulates the FL system into an MAB system, where clients are the arms and the server is the player. Then, we quantify the similarity between a local model and the server side, which is the designed metric for model aggregation and reward computation updating based on the fuzzy mathematical strategy. Next, based on the Thompson Sampling strategy, the server can intelligently determine the reward of each client, and clients with more significant rewards have the chance for local model training. With an auction method, the server can determine the training clients to reduce the training cost while maximizing each client’s revenue. Extensive experiments on real-world data sets demonstrate that the proposed scheme outperforms representative FL schemes (i.e., FedAvg, FedProx, FedMax, and MFL) regarding the model’s convergence rate and cost in FL systems with free riders.

When decoding neuroelectrophysiological signals represented by Magnetoencephalography (MEG), deep learning models generally achieve high predictive performance but lack the ability to interpret their predicted results. This limitation prevents them from meeting the essential requirements of reliability and ethical-legal considerations in practical applications. In contrast, intrinsically interpretable models, such as decision trees, possess self-evident interpretability while typically sacrificing accuracy. To effectively combine the respective advantages of both deep learning and intrinsically interpretable models, an MEG transfer approach through feature attribution-based knowledge distillation is pioneered, which transforms deep models (teacher) into highly accurate intrinsically interpretable models (student). The resulting models provide not only intrinsic interpretability but also high predictive performance, besides serving as an excellent approximate proxy to understand the inner workings of deep models. In the proposed approach, post-hoc feature knowledge derived from post-hoc interpretable algorithms, specifically feature attribution maps, is introduced into knowledge distillation for the first time. By guiding intrinsically interpretable models to assimilate this knowledge, the transfer of MEG decoding information from deep models to intrinsically interpretable models is implemented. Experimental results demonstrate that the proposed approach outperforms the benchmark knowledge distillation algorithms. This approach successfully improves the prediction accuracy of Soft Decision Tree by a maximum of 8.28%, reaching almost equivalent or even superior performance to deep teacher models. Furthermore, the model-agnostic nature of this approach offers broad application potential.

Federated Learning empowers data owners to collectively train an artificial intelligence model without exposing data. However, the heterogeneous resources and the self-interested users bring new challenges hindering the development of federated learning. To this end, we propose a Multi-attribute Auction-based Grouped Federated Learning scheme, called MAGFL, comprising a grouped federated learning framework and a multi-attribute auction-based group selection strategy. Initially, our grouped federated learning framework clusters clients into groups according to local characteristics. Then, we propose a quality assessment method to assess the quality of each group based on a fuzzy approach. Furthermore, the FL server distributes economic rewards to training clients to motivate more clients to join the FL system, which is likened to a multi-attribute auction market where each group agent bids for training opportunities. Moreover, we design a novel global model update method with added Adam (i.e., Adaptive Moment Estimation) operations into the global update stage, which can fully utilize the local and global update direction to accelerate the convergence rate of scheme MGAFL. Extensive experiments on real-world datasets demonstrate that the proposed scheme outperforms representative federated learning schemes (i.e., FedAvg, FedProx, and FedAvg-Adam) regarding the model's convergence rate and capacity to deal with heterogeneous systems.

Information-theoretic secure (ITS) authentication is an essential part of a quantum key distribution (QKD) system. In the QKD network, the authentication scheme based on the ITS QKD keys pre-shared by the QKD system. However, such a scheme is subject to the limitation that consumes a significant amount of authentication keys when the scale and communication requirements of QKD networks grow. To address the issue, we propose an ITS group authentication scheme for QKD networks that consumes considerably fewer keys. In our scheme, multiple QKD network nodes collaborate and complete the authentication as a group. Compared to the pre-shared keys authentication scheme, our scheme reduces the complexity of authentication key consumption from$O\left ({N^{2}d }\right) $to$O\left ({N }\right) $, where$N $is the number of nodes and$d $is the average path length of the network topology. The security of the proposed scheme is analyzed in detail and simulation experiments are conducted to demonstrate our scheme’s effectiveness for varying networks scales and communication requirements.

Deep learning has greatly enhanced the predictive performance of magnetoencephalography (MEG) decoding. However, the lack of interpretability has become a major obstacle to the practical application of deep learning-based MEG decoding algorithms, which may lead to non-compliance with legal requirements and distrust among end-users. To address this issue, this article proposes a feature attribution approach, which can provide interpretative support for each individual MEG prediction for the first time. The approach first transforms a MEG sample into a feature set, then assigns contribution weights to each feature using modified Shapley values, which are optimized by filtering reference samples and generating antithetic sample pairs. Experimental results show that the Area Under the Deletion test Curve (AUDC) of the approach is as low as 0.005, which means a better attribution accuracy compared to typical computer vision algorithms. Visualization analysis reveals that the key features of the model decisions are consistent with neurophysiological theories. Based on these key features, the input signal can be compressed to one-sixteenth of its original size with only a 0.19% loss in classification performance. Another benefit of our approach is that it is model-agnostic, enabling its utilization for various decoding models and brain-computer interface (BCI) applications.

Federated Learning (FL), allowing data owners to conduct model training without sending their raw data to third-party servers, can enhance data privacy in Mobile Edge Computing (MEC) which brings data processing closer to the data sources. However, the heterogeneity of local data and constrained local resources in MEC bring new challenges hindering the development of FL. To this end, we propose an Auction-based Cluster Federated Learning scheme, called ACFL, comprising a clustered FL framework and an auction-based client selection strategy. Our clustered FL framework first introduces a mean-shift clustering algorithm to FL, which can intelligently cluster clients according to their local data distribution. Then, we select clients from each cluster using an auction mechanism to participate in FL training, which can mitigate the impact of data heterogeneity on model convergence and balance energy consumption. Moreover, we prove the proposed clustered FL framework converges at a sublinear rate. Extensive experiments conducted on real-world datasets demonstrate that the proposed FL scheme outperforms the conventional FL schemes in terms of convergence rate and energy balance.

A digital-twin (DT)-enabled Internet of Medical Things (IoMT) system for telemedical simulation is developed, systematically integrated with mixed reality (MR), 5G cloud computing, and a generative adversarial network (GAN) to achieve remote lung cancer implementation. Patient-specific data from 90 lung cancer with pulmonary embolism (PE)-positive patients, with 1372 lung cancer control groups, were gathered from Qujing and Dehong, and then transmitted and preprocessed using 5G. A novel robust auxiliary classifier GAN (rAC-GAN)-based intelligent network is employed to facilitate lung cancer with the PE prediction model. To improve the accuracy and immersion during remote surgical implementation, a real-time operating room perspective from the perception layer with a surgical navigation image is projected to the surgeon’s helmet in the application layer using the DT-based MR guide clue with 5G. The accuracies of the area under the curve (AUC) of our new intelligent IoMT system were 0.92 and 0.93. Furthermore, the pathogenic features learned from our rAC-GAN model are highly consistent with the statistical epidemiological results. The proposed intelligent IoMT system generates significant performance improvement to process substantial clinical data at cloud centers and shows a novel framework for remote medical data transfer and deep learning analytics for DT-based surgical implementation.

The Tolley-Lawson(TL) model plays an important role in the aeromagnetic survey. The TLG model based on the TL model introduced the correction of the geomagnetic gradient in the real world and improved the precision of aeromagnetic compensation. The key to geomagnetic gradient compensation is to introduce the system’s position information. However, in general, there is an offset between the origin of the coordinates of the magnetometer and the fuselage, which will lead to sensor position errors, especially during maneuvers. Correcting the positional error will eliminate the offset and increase the precision of the aeromagnetic survey. In this paper, the principle of the positional error is analyzed and an improved model(TLG-C) aims to correct the positional error is proposed. The positional error is modeled as a function of the attitude angle of the aircraft and the distance between the fuselage and magnetometer. An improved aeromagnetic compensation algorithm is derived based on the TLG-C model. The results of 24 cases in actual calibration flights show that the proposed method can effectively enhance the improvement ratio.

This article presents a novel extended reality (XR) and deep-learning-based Internet-of-Medical-Things (IoMT) solution for the COVID-19 telemedicine diagnostic, which systematically combines virtual reality/augmented reality (AR) remote surgical plan/rehearse hardware, customized 5G cloud computing and deep learning algorithms to provide real-time COVID-19 treatment scheme clues. Compared to existing perception therapy techniques, our new technique can significantly improve performance and security. The system collected 25 clinic data from the 347 positive and 2270 negative COVID-19 patients in the Red Zone by 5G transmission. After that, a novel auxiliary classifier generative adversarial network-based intelligent prediction algorithm is conducted to train the new COVID-19 prediction model. Furthermore, The Copycat network is employed for the model stealing and attack for the IoMT to improve the security performance. To simplify the user interface and achieve an excellent user experience, we combined the Red Zone’s guiding images with the Green Zone’s view through the AR navigate clue by using 5G. The XR surgical plan/rehearse framework is designed, including all COVID-19 surgical requisite details that were developed with a real-time response guaranteed. The accuracy, recall, F1-score, and area under the ROC curve (AUC) area of our new IoMT were 0.92, 0.98, 0.95, and 0.98, respectively, which outperforms the existing perception techniques with significantly higher accuracy performance. The model stealing also has excellent performance, with the AUC area of 0.90 in Copycat slightly lower than the original model. This study suggests a new framework in the COVID-19 diagnostic integration and opens the new research about the integration of XR and deep learning for IoMT implementation.

To detect frame duplication in degraded videos, we proposed a coarse-to-fine approach based on locality-sensitive hashing and image registration. The proposed method consists of a coarse matching stage and a duplication verification step. In the coarse matching stage, visually similar frame sequences are preclustered by locality-sensitive hashing and considered as potential duplication candidates. These candidates are further checked by a duplication verification step. Being different from the existing methods, our duplication verification does not rely on a fixed distance (or correlation) threshold to judge whether two frames are identical. We resorted to image registration, which is intrinsically a global optimal matching process, to determine whether two frames coincide with each other. We integrated the stability information into the registration objective function to make the registration process more robust for degraded videos. To test the performance of the proposed method, we created a dataset, which consists of 3 subsets of different kinds of degradation and 117 forged videos in total. The experimental results show that our method outperforms state-of-the-art methods for most cases in our dataset and exhibits outstanding robustness under different conditions. Thanks to the coarse-to-fine strategy, the running time of the proposed method is also quite competitive.

With the development of the Energy Internet of Things (EIoT), it is of great practical significance to study the security strategy and intelligent control system for solar thermal utilization system to optimize the operation efficiency and carry out intelligent dynamic adjustment. For buildings integrated with solar water heating systems, computational fluid dynamics simulation was used in analyzing the process of solar energy output. A method based on machine learning is proposed to predict energy conversion. Besides, the simulation and analysis are carried out in combination with the possible safety problems such as the vibration of the control system. This paper proposed a novel platform of EIoT for machine learning-based cybersecurity study and implemented the platform for the temperature monitoring system. After the evaluation of the machine learning-based cybersecurity study, the EIoT system demonstrated a high performance with the Extreme Gradient Boosting (XGBoost) training algorithm.

Chronic kidney disease has become one of the diseases with the highest morbidity and mortality in kidney diseases, and there are still some problems in surgery. During the operation, the surgeon can only operate on two-dimensional ultrasound images and cannot determine the spatial position relationship between the lesion and the medical puncture needle in real-time. The average number of punctures per patient will reach 3 to 4, Increasing the incidence of complications after a puncture. This article starts with ultrasound-guided renal biopsy navigation training, optimizes puncture path planning, and puncture training assistance. The augmented reality technology, combined with renal puncture surgery training was studied. This paper develops a prototype ultrasound-guided renal biopsy surgery training system, which improves the accuracy and reliability of the system training. The system is compared with the VR training system. The results show that the augmented reality training platform is more suitable as a surgical training platform. Because it takes a short time and has a good training effect.

Summary A novel security awareness surgical navigation system has been proposed for the accurate minimally invasive surgery with machine learning algorithms, haptic‐enabled devices, and customized surgical tools to guide the surgery with real‐time force and visual navigation. To provide a direct and simplified user interface during the operation, we combined traditional surgical guide images with AR‐based view and implemented a 3D reconstructed patient‐specific surgical environment includes with all surgical requisite details. In particular, we trained the surgical collected biomechanics haptic data by employed LSTM‐based RNN algorithm, and residual network for the intraoperative force manipulation prediction and classification, respectively. Experiments evaluation results on percutaneous therapy surgery demonstrated a higher performance and distinguished accuracy by the visual and haptic combined than the traditional navigation system. These preliminary study findings may suggested a new framework in the minimally invasive surgical navigation application and hint at the possibility integration of haptic, AR, and machine learning algorithms implementation in medical simulation. In addition, we take security into account when implementation this new framework.

Inter‐frame forgery marks a central type of forgery in surveillance videos, and involves three aspects – frame duplication, insertion, and deletion – under temporal domain. However, this forgery type has received little attention from scholars. More efforts have been on detecting only a single aspect of inter‐frame forgery. Furthermore, studies have confirmed that previous methods did not achieve high accuracy for all forgeries types with low computational loads at the same time. In this study, the proposed method establishes a framework that can simultaneously detect all aspects of inter‐frame forgeries. During the decoding process, the authors extract residue data of each frame from a video stream. Then spatial and temporal energies are exploited to illustrate data flow, and abnormal points are determined to detect forged frames. Noise ratios of forged and original frames are estimated for differentiating insertion from duplication attacks. Experimental results indicate that the proposed method achieves higher accuracy and lower computational time for detecting inter‐frame forgery.

Video-assisted thoracoscopic surgery (VATS), referred to as the commonest minimum invasive excision for located T1 or T2 lung carcinomas, requires a steep learning curve for the novice residents to acquire highly deliberate skills to achieve surgical competence. The aim of this study is to propose a virtual reality-based (VR) surgical educative simulator with realistic performance in both visual and haptic sensation for the VAST procedures. To provide an immersive and perceptual user interface, we combined the customized haptic-enabled thoracoscopic instruments with HTC VIVE helmet set in our simulation system. In particular, position based deformation (PBD) method on the GPU and a novel haptic rendering algorithm of surgical grasps and stapling operations are also been implemented for the surgical scene, respectively for the soft tissue deformation and intraoperative force manipulation simulation. Experiments by thoracic surgery professors and novices' evaluation results on our framework demonstrated a high performance and distinguished accurately. These study findings suggested a new cognitive model for the VATS surgical education integrate with haptic and VR implementation.

Percutaneous therapy is a common clinical operation in minimally invasive surgery. Yet, learning curve of this skillful manual operation is steep, which imposes negative impacts on its further advances. In this paper, we proposed a novel workflow to simulate percutaneous therapy through visuo-haptic rendering based on the clinical trials. Intraoperative puncture data, obtained by our 6DOF force recording system in the operating room, is fitted as the original force model for the haptic rendering. Patient-specific medical images were also segmented and reconstructed for the highly immersive virtual training scenario. Last but not least, medical professors and novices have also been invited to practice on our training scenario by employed the Global Rating Scale (GRS) questionnaire and parameter metrics recording to validate framework's performance. Posttest values in experts and novices' groups after training showed great progress with respect to pretest values in both GRS scores and objective evaluation.

Since the Quantum Key Distribution (QKD)technique makes it possible to construct an absolute secure cryptographic system by combing the One-time pad, QKD has drawn many attention these years. The insufficient implementation speed of the post-processing system of QKD is one of the greatest obstacle to wide application of QKD. The sifting module of QKD post-processing system needs to deal with the heaviest incoming load, it is of crucial importance to study how to design and implement an efficient sifting module to accelerate the QKD post-processing system. In this paper, an efficient FPGA based design scheme of the sifting module is presented. Our scheme can decrease the demands for storage resource and communication traffic obviously.

A novel multimodal biometric recognition algorithm based on complex kernel fisher discriminant analysis (complex KFDA) is proposed. Complex KFDA exploits two phases to generalize KFDA and perform classification for the fusion feature set: complex KPCA plus complex LDA. As two distinct biometric modals, the features of iris and face are fused in parallel to test our algorithm. Experimental results show that the proposed algorithm achieves much better performance than other conventional multimodal biometric algorithms.