Semantic segmentation of remote sensing (RS) image is crucial to tasks such as geographic research, land monitoring and environmental protection. In recent years, deep learning models built with convolutional neural networks (CNNs) and Transformer structures have proven effective in semantic segmentation task of RS images. With the increase in resolution of RS images in complex scenes and the complexity of high-resolution urban images, each object has rich textures and edges, and the distribution of objects is extremely irregular. To resolve above challenges, a semantic segmentation network for RS images is proposed, which employs an encoder-decoder structure, where four ResNet-18 blocks act as encoders, and four specially designed local-contextual Transformer blocks form the decoder. In order to effectively utilize local contextual features, a channel attention-feature fusion module using a novel nonlinear spiking neuron model is designed to assist the decoder in better feature recovery. The experimental results demonstrate that the proposed method is feasible and effective for semantic segmentation of RS images. Specifically, the suboptimal 86.42% and optimal 82.25% mIoU are achieved on Potsdam and Vaihingen datasets, respectively, and the best 52.4% and the near-optimal 65.3% mIoU on the LoveDA and UAVid datasets, respectively, for the proposed model.

Multivariate workload prediction in cloud computing environments is a critical research problem. Effectively capturing inter-variable correlations and temporal patterns in multivariate time series is key to addressing this challenge. To address this issue, this paper proposes a convolutional model based on a Nonlinear Spiking Neural P System (ConvNSNP), which enhances the ability to process nonlinear data compared to conventional convolutional models. Building upon this, a hybrid forecasting model is developed by integrating ConvNSNP with a Bidirectional Long Short-Term Memory (BiLSTM) network. ConvNSNP is first employed to extract temporal and cross-variable dependencies from the multivariate time series, followed by BiLSTM to further strengthen long-term temporal modeling. Comprehensive experiments are conducted on three public cloud workload traces from Alibaba and Google. The proposed model is compared with a range of established deep learning approaches, including CNN, RNN, LSTM, TCN and hybrid models such as LSTNet, CNN-GRU and CNN-LSTM. Experimental results on three public datasets demonstrate that our proposed model achieves up to 9.9% improvement in RMSE and 11.6% improvement in MAE compared with the most effective baseline methods. The model also achieves favorable performance in terms of MAPE, further validating its effectiveness in multivariate workload prediction.

With the integration of intelligent medical devices and wireless sensor networks, telemedicine queries have significantly enhanced the efficiency and accessibility of medical services. However, the security and privacy of medical query records remain a critical challenge. While existing privacy-preserving query frameworks in Wireless Body Area Networks (WBANs) primarily focus on protecting the privacy of medical records, they often lack robust mechanisms for authenticating query users. This deficiency may enable malicious entities to gain unauthorized access, thereby resulting in data leakage. To address this issue, we propose a privacy-preserving query scheme with unlinkability by integrating double-Schnorr-based anonymous authentication and 1-out-of-n oblivious transfer (OT). Specifically, anonymous authentication is achieved via a double-Schnorr-based credential construction with session-dependent pseudonym blinding, enabling the server to verify user legitimacy without revealing users’ real identities. OT is implemented through a short-hash-based keyword partition mechanism and masked encryption, ensuring that the curious server cannot infer user queries while fulfilling them correctly. Additionally, query privileges are restricted to legitimate users by verifying anonymous credentials issued during the registration phase. The formal security analysis confirms that the proposed scheme achieves essential security attributes, including anonymous authentication, query privacy, and unlinkability. Experimental results demonstrate that the proposed scheme not only integrates anonymous authentication but also outperforms baseline schemes in both computational and communication efficiency. Therefore, the proposed scheme is more suitable for real-world deployment within IoT-based healthcare ecosystems.

Due to the differences in size, shape, and location of brain tumors, brain tumor segmentation differs greatly from that of other organs. The purpose of brain tumor segmentation is to accurately locate and segment tumors from MRI images to assist doctors in diagnosis, treatment planning and surgical navigation. NSNP-like convolutional model is a new neural-like convolutional model inspired by nonlinear spiking mechanism of nonlinear spiking neural P (NSNP) systems. Therefore, this paper proposes a global-local feature fusion network based on NSNP-like convolutional model for MRI brain tumor segmentation. To this end, we have designed three characteristic modules that take full advantage of the NSNP-like convolution model: dilated SNP module (DSNP), multi-path dilated SNP pooling module (MDSP) and Poolformer module. The DSNP and MDSP modules are employed to construct the encoders. These modules help address the issue of feature loss and enable the fusion of more high-level features. On the other hand, the Poolformer module is used in the decoder. It processes features that contain global context information and facilitates the interaction between local and global features. In addition, channel spatial attention (CSA) module is designed at the skip connection between encoder and decoder to establish the long-range dependence between the same layers, thereby enhancing the relationship between channels and making the model have global modeling capabilities. In the experiments, our model achieves Dice coefficients of 85.71[Formula: see text], 92.32[Formula: see text], 87.75[Formula: see text] for ET, WT, and TC, respectively, on the N-BraTS2021 dataset. Moreover, our model achieves Dice coefficients of 83.91[Formula: see text], 91.96[Formula: see text], 90.14[Formula: see text] and 85.05[Formula: see text], 92.30[Formula: see text], 90.31[Formula: see text] on the BraTS2018 and BraTS2019 datasets respectively. Experimental results also indicate that our model not only achieves good brain tumor segmentation performance, but also has good generalization ability. The code is already available on GitHub: https://github.com/Li-JJ-1/NSNP-brain-tumor-segmentation.

Although a variety of deep learning-based methods have been introduced for Salient Object Detection (SOD) to RGB and Depth (RGB-D) images, existing approaches still encounter challenges, including inadequate cross-modal feature fusion, significant errors in saliency estimation due to noise in depth information, and limited model generalization capabilities. To tackle these challenges, this paper introduces an innovative method for RGB-D SOD, TranSNP-Net, which integrates Nonlinear Spiking Neural P (NSNP) systems with Transformer networks. TranSNP-Net effectively fuses RGB and depth features by introducing an enhanced feature fusion module (SNPFusion) and an attention mechanism. Unlike traditional methods, TranSNP-Net leverages fine-tuned Swin (shifted window transformer) as its backbone network, significantly improving the model's generalization performance. Furthermore, the proposed hierarchical feature decoder (SNP-D) notably enhances accuracy in complex scenes where depth noise is prevalent. According to the experimental findings, the mean scores for the four metrics S-measure, F-measure, E-measure and MEA on the six RGB-D benchmark datasets are 0.9328, 0.9356, 0.9558 and 0.0288. TranSNP-Net achieves superior performance compared to 14 leading methods in six RGB-D benchmark datasets.

Thermal and RGB images exhibit significant differences in information representation, especially in low-light or nighttime environments. Thermal images provide temperature information, complementing the RGB images by restoring details and contextual information. However, the spatial discrepancy between different modalities in RGB-Thermal (RGB-T) semantic segmentation tasks complicates the process of multimodal feature fusion, leading to a loss of spatial contextual information and limited model performance. This paper proposes a channel-space fusion nonlinear spiking neural P system model network (CSPM-SNPNet) to address these challenges. This paper designs a novel color-thermal image fusion module to effectively integrate features from both modalities. During decoding, a nonlinear spiking neural P system is introduced to enhance multi-channel information extraction through the convolution of spiking neural P systems (ConvSNP) operations, fully restoring features learned in the encoder. Experimental results on public datasets MFNet and PST900 demonstrate that CSPM-SNPNet significantly improves segmentation performance. Compared with the existing methods, CSPM-SNPNet achieves a 0.5% improvement in mIOU on MFNet and 1.8% on PST900, showcasing its effectiveness in complex scenes.

Deep learning technology has been successfully used in Chest X-ray (CXR) images of COVID-19 patients. However, due to the characteristics of COVID-19 pneumonia and X-ray imaging, the deep learning methods still face many challenges, such as lower imaging quality, fewer training samples, complex radiological features and irregular shapes. To address these challenges, this study first introduces an extensive NSNP-like neuron model, and then proposes a multitask adversarial network architecture based on ENSNP-like neurons for chest X-ray images of COVID-19, called MAE-Net. The MAE-Net serves two tasks: (i) converting low-quality CXR images to high-quality images; (ii) classifying CXR images of COVID-19. The adversarial architecture of MAE-Net uses two generators and two discriminators, and two new loss functions have been introduced to guide the optimization of the network. The MAE-Net is tested on four benchmark COVID-19 CXR image datasets and compared them with eight deep learning models. The experimental results show that the proposed MAE-Net can enhance the conversion quality and the accuracy of image classification results.

Most existing multi-scale object detectors depend on multi-level feature maps. The Feature Pyramid Networks (FPN) is a significant architecture for object detection that utilizes these multi-level feature maps. However, the use of FPN also increases the detector's complexity. For object detection methods that only use a single-level feature map, the detection performance is limited to some extent because the single-level feature map cannot balance deep semantic information and shallow detail information. We introduce a novel detector - the Spiking Neural P Multiple-in-Single-out (SNPMiSo) detector to address these challenges. The SNPMiSo detector is constructed based on SNP-like neurons. In SNPMiSo, we employ two kinds of Transformers to boost the important features across different-level feature maps separately. After enhancing the features, we use an incremental upsampling module to upsample and merge the two feature maps. This combined feature map is input into the NAF dilated residual module and the NAF dual-branch detection head. This process allows us to extract multi-scale features and carry out detection tasks. Our tests show promising results: On the COCO dataset, SNPMiSo attains an Average Precision (AP) of 38.7, an improvement of 1.0 AP over YOLOF. In addition, SNPMiSo demonstrates a quicker detection speed, outperforming some advanced multi-level and single-level object detectors.

Referring image segmentation aims to accurately align image pixels and text features for object segmentation based on natural language descriptions. This paper proposes NSNPRIS (convolutional nonlinear spiking neural P systems for referring image segmentation), a novel model based on convolutional nonlinear spiking neural P systems. NSNPRIS features NSNPFusion and Language Gate modules to enhance feature interaction during encoding, along with an NSNPDecoder for feature alignment and decoding. Experimental results on RefCOCO, RefCOCO[Formula: see text], and G-Ref datasets demonstrate that NSNPRIS performs better than mainstream methods. Our contributions include advances in the alignment of pixel and textual features and the improvement of segmentation accuracy.

Seizure is a common neurological disorder that usually manifests itself in recurring seizure, and these seizures can have a serious impact on a person's life and health. Therefore, early detection and diagnosis of seizure is crucial. In order to improve the efficiency of early detection and diagnosis of seizure, this paper proposes a new seizure detection method, which is based on discrete wavelet transform (DWT) and multi-channel long- and short-term memory-like spiking neural P (LSTM-SNP) model. First, the signal is decomposed into 5 levels by using DWT transform to obtain the features of the components at different frequencies, and a series of time-frequency features in wavelet coefficients are extracted. Then, these different features are used to train a multi-channel LSTM-SNP model and perform seizure detection. The proposed method achieves a high seizure detection accuracy on the CHB-MIT dataset: 98.25% accuracy, 98.22% specificity and 97.59% sensitivity. This indicates that the proposed epilepsy detection method can show competitive detection performance.

Deep convolutional neural networks have shown advanced performance in accurately segmenting images. In this paper, an SNP-like convolutional neuron structure is introduced, abstracted from the nonlinear mechanism in nonlinear spiking neural P (NSNP) systems. Then, a U-shaped convolutional neural network named SNP-like parallel-convolutional network, or SPC-Net, is constructed for segmentation tasks. The dual-convolution concatenate (DCC) and dual-convolution addition (DCA) network blocks are designed, respectively, in the encoder and decoder stages. The two blocks employ parallel convolution with different kernel sizes to improve feature representation ability and make full use of spatial detail information. Meanwhile, different feature fusion strategies are used to fuse their features to achieve feature complementarity and augmentation. Furthermore, a dual-scale pooling (DSP) module in the bottleneck is designed to improve the feature extraction capability, which can extract multi-scale contextual information and reduce information loss while extracting salient features. The SPC-Net is applied in medical image segmentation tasks and is compared with several recent segmentation methods on the GlaS and CRAG datasets. The proposed SPC-Net achieves 90.77% DICE coefficient, 83.76% IoU score and 83.93% F1 score, 86.33% ObjDice coefficient, 135.60 Obj-Hausdorff distance, respectively. The experimental results show that the proposed model can achieve good segmentation performance.

Federated learning (FL) emerges as a promising paradigm, relentlessly pursuing excellence in efficiency, privacy preservation, and security—the holy trinity that underpins the fundamental philosophy and practical implementation of FL. However, previous scholarly works have predominantly focused on the privacy protection and secure aggregation in the realm of FL. Undoubtedly, efficiency still plays a pivotal role in determining FL’s viability in real-world applications. To improve efficiency while ensuring privacy protection and secure aggregation, this work proposes a verifiable privacy-preserving federated learning framework tailored for practical applications. Firstly, a novel aggregation rule, constrained M maximum security aggregation, forces the server to securely aggregate the local gradients from M users without relying on any auxiliary servers, thereby considerably decreasing the communication overhead. Secondly, regardless of the dimension of the aggregated gradient being verified, our scheme performs a single verification per user per round. Through security analysis, our scheme could guarantee some given security requirements. Besides, extensive experiments show that under the proportion that the gradient dimension$(d)$to the number of users$(n)$is 1:2 and 2:1, ours is$\times 1.3$and$\times 1$faster for total runtime and is$\times 3$and$\times 7$lower for total communication cost compared with a state-of-the-art framework, respectively. Therefore, our FL framework is more suitable for practical application in real life.

Blockchain-based authentication, as a distributed system, is a significant method to achieve secure service access and provision for the distributed mobile cloud computing (MCC) environment. However, owing to the transparency of blockchain, it remains a challenge to protect users’ access behavior from disclosure. Besides, billions of users in the MCC system may cause storage bottlenecks to the blockchain network. To overcome these challenges, this paper designs two blockchain-based privacy-preserving authentication schemes supporting hierarchical access control for the MCC environment. Both schemes allow users to access multiple services with different permissions after a single registration. To address the challenges of privacy disclosure, we use polynomial commitment to replace the plaintext on the blockchain. Meanwhile, a new verification and updating of the access permission method is proposed using the homomorphic property of polynomial commitment. The first scheme works toward reducing computation costs, which is more suitable for systems with a limited number of service providers (SPs). On the other hand, the second scheme aims to reduce the storage requirements of blockchain, and it provides more efficient hierarchical access control for large-scale scenarios without requiring more storage space. Then, the security analysis demonstrates that the two schemes satisfy multiple security requirements. Finally, a comparative summary is presented to show that our schemes have good performance in computation and communication efficiency and are well suited to the MCC system.

Nonlinear spiking neural P (NSNP) systems are one of neural-like membrane computing models, abstracted by nonlinear spiking mechanisms of biological neurons. NSNP systems have a nonlinear structure and can show rich nonlinear dynamics. In this paper, we introduce a variant of NSNP systems, called gated nonlinear spiking neural P systems or GNSNP systems. Based on GNSNP systems, a recurrent-like model is investigated, called GNSNP model. Moreover, exchange rate forecasting tasks are used as the application background to verify its ability. For the purpose, we develop a prediction model based on GNSNP model, called ERF-GNSNP model. In ERF-GNSNP model, the GNSNP model is followed by a "dense" layer, which is used to capture the correlation between different sub-series in multivariate time series. To evaluate the prediction performance, nine groups of exchange rate data sets are utilized to compare the proposed ERF-GNSNP model with 25 baseline prediction models. The comparison results demonstrate the effectiveness of the proposed ERF-GNSNP model for exchange rate forecasting tasks.

In the last few years, mobile cloud computing (MCC) gains a huge development because of the popularity of mobile applications and cloud computing. User authentication and access control are two indispensable security components in the MCC environment. To the best of our knowledge, they are generally designed in different procedures. Access control can be executed after the authentication completes successfully. In order to improve efficiency, this article constructs an integrated scheme of authentication and hierarchical access control using self-certified public key cryptography (SCPKC) and the Chinese remainder theorem (CRT) for MCC environment. The proposed scheme can achieve mutual authentication while determining the access rights of mobile users without storing any access control list in the MCC service provider side. Besides, we also give a dynamic adding or deletion of MCC service provider to efficiently address potential changes in the hierarchy. The security of our proposed scheme is proved by the random oracle model. Compared with recently related multi-server authentication schemes for the MCC environment, the proposed scheme not only adds a new function of hierarchical access control but also has better computation and communication efficiencies. Therefore, the proposed scheme is more suitable for real-life MCC applications.