Pneumonia has long been a significant concern in global public health. With the advancement of convolutional neural networks (CNNs), new technological methods have emerged to address this challenge. However, the application of CNNs to pneumonia diagnosis still faces several critical issues. First, the datasets used for training models often suffer from insufficient sample sizes and imbalanced class distributions, leading to reduced classification performance. Second, although CNNs can automatically extract features and make decisions from complex image data, their interpretability is relatively poor, limiting their widespread use in clinical diagnosis to some extent. To address these issues, a novel weighted cross-entropy loss function is proposed, which calculates weights via an inverse proportion exponential function to handle data imbalance more efficiently. Additionally, we employ a transfer learning approach that combines pretrained CNN model parameter fine-tuning to improve classification performance. Finally, we introduce the gradient-weighted class activation mapping method to enhance the interpretability of the model’s decisions by visualizing the image regions of focus. The experimental results indicate that our proposed approach significantly enhances CNN performance in pneumonia diagnosis tasks. Among the four selected models, the accuracy rates improved to over 90%, and visualized results were provided.

The secure and effective dissemination of logistics data is frequently obstructed by issues pertaining to ownership verification and unwanted access during data exchange. This study introduces an innovative strategy for data ownership verification and regulated sharing based on the notion of “three rights separation”, which delineates data ownership into control rights, usage rights, and management rights. The proposed approach incorporates chameleon signatures and blockchain technology to facilitate dynamic, non-falsifiable ownership marking and verification. Additionally, it utilizes searchable encryption and proxy re-encryption methods to guarantee that data are viewed solely under allowed circumstances, thereby averting misuse by third-party data administrators. Security analysis verifies resilience against adaptive chosen-message assaults and keyword-guessing threats, while simulation studies illustrate the scheme’s robustness, efficiency, and practical applicability in real-world logistical settings. This framework offers a scalable and safe solution for multi-party data sharing with explicitly defined ownership control.

In the context of global digital economic integration, reliable and advanced cloud computing is playing an increasingly pivotal role in the logistics sector, especially in long-haul trunk logistics. The diverse characteristics of Logistics Information Systems, along with the necessity to handle substantial data volumes and adhere to stringent data protection regulations from several stakeholders, present considerable obstacles to information flow and sharing. This issue is particularly pronounced in China’s logistics sector, which is predominantly comprised of small and medium-sized firms (SMEs). This study offers the Hyperconnected Trunk Logistics Alliance (HTLA) framework to tackle these difficulties by utilizing blockchain and big data technologies. The framework seeks to diminish obstacles between diverse systems employed by various stakeholders and promote the integration of Logistics Information Systems while safeguarding data privacy. The suggested data privacy solution ensures data confidentiality within the network and implements access control via smart contracts on a distributed ledger. The UILA platform is an innovative solution that fosters collaboration among stakeholders and elevates logistics service standards. The implementation of the “China National Logistics Hub Project” has shown significant efficacy in creating a reliable, cooperative, and transparent logistics network system, underscoring its potential for widespread application and practical utility.