We propose a Cross-Modal Contrastive Learning (CMCL) framework that integrates multimodal MRI features extracted from resting-state functional magnetic resonance imaging (Rs-fMRI) and voxel-based morphometry (VBM), aiming to identify drug addiction circuits in the brain. To enhance structural information modeling, we introduce, for the first time, a structural covariance graph constructed based on the cosine similarity of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) volumes. This graph is combined with a functional connectivity graph derived from traditional Pearson correlation, enabling unified modeling of functional and structural information. CMCL aligns the latent representations of functional and structural modalities through a contrastive learning mechanism, effectively capturing multiscale brain network abnormalities associated with addiction and revealing functional-structural coupling changes in reward and executive control circuits. To address the inadequate interaction modeling in traditional multimodal approaches, we design a unified feature embedding module, an improved InfoNCE loss function, and a complementary loss to mitigate cross-modal heterogeneity and enhance cross-modal complementarity. Experimental results on a drug addiction dataset demonstrate that CMCL significantly outperforms existing methods in classification performance. Moreover, the learned subgraph structures closely match clinical findings, accurately identifying key brain regions and pathways related to drug addiction. These results highlight the functional-structural co-alteration patterns induced by addiction and provide a novel methodological support for addiction mechanism research and clinical auxiliary diagnosis.

Diffuse reflectance spectroscopy exploits multiple scattering and absorption of light in superficial tissue to capture characteristic spectral signatures. When combined with machine learning, this approach enables accurate, real-time, non-invasive detection. Conventional drug screening methods, based on biochemical assays of urine, blood, or hair are limited by their invasiveness, long turnaround time, high cost, and poor portability that hinder their use in rapid, large-scale applications. To address these limitations, we propose a fast, efficient, and high-accuracy non-invasive drug screening framework that integrates diffuse reflectance spectroscopy with sex-stratified machine learning models. A skin spectral trace element database was established using data collected from over two thousand individuals. Two sequential classification pipelines were developed: support vector machines for male subjects and an Extreme Gradient Boosting for female subjects. In a case study focused on heroin detection, both models achieved high classification accuracy and demonstrated strong performance in terms of the area under the receiver operating curve. This approach provides a practical solution for preliminary drug screening and demonstrates the promise of combining optical spectroscopy with artificial intelligence for real-world drug surveillance.

This study proposes a medical image reversible information hiding method based on the difference of pixel difference (DPD) histogram regionalization. Given the complex structure and rich texture details of medical images, the original image is first subjected to adaptive neighboring pixel interpolation expansion processing to divide it into seed pixels and nonseed pixels, thereby enhancing image resolution and embedding space redundancy. Subsequently, the deep learning model U-Net is employed to segment the image into regions. By constructing a DPD histogram, high-frequency and structurally abrupt regions in the image are extracted, enabling precise identification of sensitive areas. Based on this, a dual-threshold decision mechanism is employed to apply different information embedding strategies to distinct regions, thereby enhancing embedding capacity and interference resistance. Extensive experiments demonstrate that this method not only maintains extremely high visual quality (average peak signal-to-noise ratio PSNR exceeding 46 dB) but also significantly enhances information embedding capacity. This technology provides robust security for the transmission and storage of medical images in telemedicine and electronic health record systems, opening new research directions and prospects for application in the field of hiding medical image information.

In IoT data sharing, game-theoretic data pricing is widely recognized for its dynamic equilibrium and payoff maximization but faces challenges in real-time performance, integrity, and reliability. This paper proposes a Secure Gametheoretic Framework (SGF) using OP-TEE for secure and efficient game processes, with results uploaded to the blockchain for traceability. The paper also improves the iterative solution of the Stackelberg evolutionary game model to accelerate convergence. Experimental results on the Raspberry Pi 3B shows that the proposed framework completes the pricing process under 3 minutes with approximately 1000 nodes participate in the game, meeting the real-time IoT data sharing requirements. the additional overhead from OP-TEE stays under 15%, balancing security and performance. The improved method reduces time cost by 52.65% and 64.05% compared to existing methods, demonstrating significant effectiveness.

With the increasing attention to privacy protection issues in the field of distributed machine learning, how to empower users with the “right to be forgotten” in federated learning has become an important research direction. We propose a multi feature joint unlearning method to improve privacy protection and model management efficiency in federated learning. By assigning a learnable mask weight to each feature, dynamically adjust the contribution of each feature in the unlearning process. This method not only effectively avoids conflicts between features, but also significantly improves the stability and efficiency of the unlearning process. Meanwhile, sparse regularization ensures the focus of the unlearning process and avoids unnecessary feature unlearning. In addition, the integration of blockchain enhances the transparency and security of the system, ensuring the immutability and traceability of all update operations. In the experimental section, we validated the effectiveness of the method on multiple datasets, particularly on complex datasets where metrics such as accuracy, feature sensitivity, and attack success rate performed well, providing an effective solution for the feature unlearning problem in federated learning.

Delegated Proof of Stake (DPoS) is a widely utilized consensus protocol in blockchain-based Internet of Things (IoT) systems. We propose a heuristic algorithm-based accounting rights allocation method, also referred to as the witness election method, which aims to address the challenges in DPoS. The challenges associated with selected witness nodes that do not reflecting majority stakeholder preferences and susceptibility to manipulation of the vote. This method employs the Kendall’s rank correlation as the fitness function to optimize the arrangement of the top-k producers, thereby maximizing stakeholder preferences. We propose a novel heuristic algorithm, termed SP-DEWOA, which combines the differential evolution algorithm and whale optimization with piecewise chaotic mapping to maximize permutation similarity, i.e., stakeholder preferences. To further improve the efficiency of SP-DEWOA, we parallelize SP-DEWOA based on the Spark-based parallelization design. Experimental results demonstrate that the witness nodes selected through SP-DEWOA are consistent with the preferences of the majority of stakeholders. Furthermore, SP-DEWOA has been proven to have high scalability and resilience against vote manipulation.

The identity resolution system serves as the entrance for the Internet of Things (IoT) data, ensuring unique identification of devices and effective data exchange. However, current identity resolution systems face issues such as information silos, uneven distribution of permissions, difficulties in manually managing identifiers for large-scale applications, and security weakness. Therefore, this paper proposes a compatible, fair, automated, and secure identity resolution system named RBBC, which serves as a universal portal for IoT device identification, data retrieval, and data exchanges. RBBC introduces a universal architecture to achieve compatibility in identity resolution, breaking down the information silos within the system; it decentralizes management authority to participants, realizing automated, fair, and equitable identifier management; it utilizes blockchain to ensure the immutability of identifiers and introduces a reputation model with an incentive mechanism into the blockchain to provide a quantifiable and sustainable trust measure for the system, thereby enhancing the security and reliability of identity resolution. Lastly, experimental validation confirms the effectiveness of the reputation model in detecting malicious nodes, and the efficiency of the automatic identifier allocation and registration mechanism, demonstrating the study's suitability for large-scale networks.

Electrical stimulation of the peripheral nervous system is a promising therapeutic option for several conditions; however, its effects on tissue and the safety of the stimulation remain poorly understood. In order to devise stimulation protocols that enhance therapeutic efficacy without the risk of causing tissue damage, we constructed computational models of peripheral nerve and stimulation cuffs based on extremely high-resolution cross-sectional images of the nerves using the most recent advances in computing power and machine learning techniques. We developed nerve models using nonstimulated (healthy) and over-stimulated (damaged) rat sciatic nerves to explore how nerve damage affects the induced current density distribution. Using our in-house computational, quasi-static, platform, and the Admittance Method (AM), we estimated the induced current distribution within the nerves and compared it for healthy and damaged nerves. We also estimated the extent of localized cell damage in both healthy and damaged nerve samples. When the nerve is damaged, as demonstrated principally by the decreased nerve fiber packing, the current penetrates deeper into the over-stimulated nerve than in the healthy sample. As safety limits for electrical stimulation of peripheral nerves still refer to the Shannon criterion to distinguish between safe and unsafe stimulation, the capability this work demonstrated is an important step toward the development of safety criteria that are specific to peripheral nerve and make use of the latest advances in computational bioelectromagnetics and machine learning, such as Python-based AM and CNN-based nerve image segmentation.