Session-based recommendation (SBR) refers to a technique that recommends relevant content based on user behavior and contextual information during short-term interaction sessions. Previous SBR models that relied on limited short-term behavioral data, failing to fully utilize other valuable information, have suffered a lot from the problem of data sparsity. Short-term user interactions influenced by long-range dependencies, and past session-based recommendation models often failed to capture more complex dependency relationships, affecting recommendation performance. This paper proposes a novel session-based recommendation model called Intent Aggregation and Category Enhanced Graph Neural Network (IC-GNN). The model determines user preferences by learning item representations using a modular gated attention network and a category aggregator.Specifically, IC-GNN learns item representations in two ways. The first way is to use item embeddings to generate intent representations, which are aggregated through multi-layer gated aggregation and residual connections to produce global-level item representations. The second way is to construct a session graph from user interaction sequences and use graph neural networks to generate session-level representations for the current session. Then, a category-enhanced aggregator integrates item-category information into the session-level representation. Finally, the model also uses a nonlinear feature aggregation module to explore similarities within session features and identify relationship patterns between local items. Experiments on three real-world datasets show that IC-GNN outperforms many advanced models in terms of performance.

Images captured in foggy conditions often suffer from low visibility, high noise levels, and missing detailed information, posing significant challenges to object detection in autonomous vehicles. To address these challenges, this paper proposes a foggy-weather object detection method based on YOLOv8n, tentatively named Group Spatial Deformable YOLO (GSDYOLO). The dark channel prior dehazing algorithm enhances data by processing the dark channel of input images to achieve dehazing effects. Furthermore, the introduction of the Grouped Partial Deformable Module (GPDM)into the backbone enhances the model’s feature extraction and representation capabilities. The Spatially-Enhanced Cross Stage Network (SECSN) module is proposed for the neck, enabling the capture and effective utilization of multi-scale features to generate discriminative features across various scales. Additionally, an Enhanced Bidirectional Feature Pyramid Network (EBiFPN) was adopted, incorporating a weighted bidirectional feature pyramid network (top-down and bottom-up) and introducing a P6 large-object output layer to improve the network’s feature extraction and detection capabilities. Experimental results demonstrate that these improvements effectively enhance the detection performance of blurred and small objects under foggy conditions. The mean average precision (mAP) on the RTTS and synthetic VOC FOG datasets increased by 3.3% and 2.8%, respectively. The experimental model exhibits superior performance and robustness, providing technical support for the fast and accurate detection of objects by autonomous vehicles in foggy and other adverse weather conditions.

The management of complex diseases and patient-centered personalized needs is increasingly demanding. While significant progress has been made in research on single-objective disease management and personalized medicine, there remains a lack of an integrated solution for coordinating multi-objective strategies and dynamically adjusting personalized approaches. This paper introduces a decision support system based on a computer-argumentation engine. This system builds an evidence-based knowledge repository from clinical and rehabilitation guidelines and constructs a patient-centered hierarchical conceptual framework for PROMs to evaluate goal realization benefits. It automates the recommendation of optimal treatments based on the reasoning of conflicts between objectives, incorporating patient preferences and priority of objectives to dynamically adjust daily health management decisions. Through a regular feedback mechanism via PROMs, the system iteratively updates and dynamically adjusts its argumentation based on user states and preferences. A prototype system has been designed and implemented, focusing on multi-objective management for breast cancer patients, to demonstrate the feasibility of this system.

Agents in medical decision support have been extensively researched, particularly in areas like evidence support, multimorbidity management, and patient-specific needs. However, current approaches lack a unified method to address real-time evidence updates, manage multiple diseases independently, and incorporate personalized patient needs. Existing Large Language Model (LLM) agents are limited by their reliance on static knowledge bases, hindering their ability to promptly update clinical guidelines and meet diverse patient requirements. Moreover, the interpretability of LLMs remains a significant concern, leading to skepticism in their medical application. To address these challenges, we developed MedGen, a multi-agent architecture that decomposes the clinical decision-making process into stages such as clinical goal setting, data collection, argumentation linking, and plan selection. This structured approach allows LLM agents to provide both reasoning evidence and a transparent reasoning process, enhancing the reliability and interpretability of outcomes. Finally, a case study of breast cancer and depression is combined to illustrate our architecture.

Clinical decision support is aimed at delivering the best evidence available encapsulated in practice guidelines. The current challenges in reaching this goal include keeping guidelines up-to-date, linking them to address multi-morbidity, and flexible customization to fit patient preferences. Although a variety of solutions have been proposed to address these challenges, a comprehensive approach for their systematic integration remains absent. We propose PICOAS, a knowledge linking model composed of three modes, to establish the relationship between knowledge sources of guidelines, medical literature, and patient reviews. An LLM-Agent architecture is developed, which is capable of understanding and providing decision support informed by the knowledge link model. We demonstrate the feasibility and effectiveness of our approach using a study of breast cancer. An experiment was conducted for evaluating its capabilities in addressing the three challenges.

Clinical decision support systems (CDSS) assist physicians in making medical decisions by relying on fixed rules and guidelines. However, these systems often lack sufficient consideration of individual differences and struggle to adapt to complex clinical scenarios. This paper proposes a novel CDSS based on an extended argumentation framework, integrating patient data and individual preferences to provide more personalized treatment recommendations. By employing critical questions and argument schemes from computational argumentation, and utilizing multiple data sources—including official medical guidelines, comprehensive drug information databases, and patient reviews—we enhance the system's decision-making capability. We developed a prototype system to validate this approach and its outcomes.

In the sixth-generation (6G) Internet of Everything (IoE) environment, integrated sensing and communication (ISAC) can improve the utilization of radio resources. The application of reconfigurable intelligent surface (RIS) and millimeter wave (mmWave) can improve the performance of the ISAC. In this article, we propose an ISAC algorithm for RIS-assisted multiuser mmWave multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. The proposed ISAC algorithm can achieve simultaneous channel estimation, positioning and environment mapping. Considering the limited robustness of the traditional algorithms to noise, the proposed algorithm first uses a complex-valued depth residual convolution neural network (C-DRCNN)-assisted channel estimation algorithm by using the powerful computational power of deep learning. Further, the sparsity of the mmWave channel can be utilized by the parallel factor (PARAFAC) tensor decomposition for obtaining the factor matrices, which contain the channel parameters, such as direction-of-arrival (DOA), direction-of-departure (DOD), time delay (TD), and complex path gain. Finally, the multiuser positioning and environment mapping are realized according to the geometric relationship between the position and channel parameters. The simulation results demonstrate that the proposed algorithm achieves better channel estimation, multiuser positioning and environment mapping performance compared with the state-of-the-art algorithm. In addition, since the proposed algorithm integrates the deep neural network and tensor decomposition, it still has excellent ISAC performance even at low signal-to-noise ratio (SNR).

This paper describes the process of embedding ChatGPT-4 (Large Scale Natural Language Modeling) in a CDSS (Clinical Decision Support System) to generate multiple types of decision recommendations. First, given enquiry data, the CDSS generates a specific type of decision recommendations and gives the questions and answers to ChatGPT-4 to generate the related type of decision recommendations. To categorize the same type of decision recommendations in CDSS and ChatGPT-4 together, Word2Vec model was used to learn the semantic relationships of words in medical texts and evaluate the model. Then, the similarity between the decision recommendations generated by CDSS and ChatGPT-4 is determined by calculating the cosine similarity, and a suitable threshold is set to decide whether to fuse these decision recommendations or not. Through this method, the decision recommendations generated by CDSS and ChatGPT-4 can be effectively fused to provide more comprehensive and precise clinical decision support.