OrthoNets use the Gram-Schmidt process to achieve orthogonality among filters but do not impose constraints on the internal orthogonality of individual filters. To reduce the risk of overfitting, especially in scenarios with limited data such as medical image, this study explores an enhanced network that ensures the internal orthogonality within individual filters, named the Orthogonal Channel Shuffle Network ( OSNet). This network is integrated into the Detection Transformer (DETR) framework for brain tumor detection, resulting in the OS-DETR. To further optimize model performance, this study also incorporates deformable attention mechanisms and an Intersection over Union strategy that emphasizes the internal region influence of bounding boxes and the corner distance disparity. Experimental results on the Br35H brain tumor dataset demonstrate the significant advantages of OS-DETR over mainstream object detection frameworks. Specifically, OS-DETR achieves a Precision of 95.0%, Recall of 94.2%, mAP@50 of 95.7%, and mAP@50:95 of 74.2%. The code implementation and experimental results are available at https://github.com/dkx2077/OS-DETR.git.

In the recent advancements of recommendation systems, the integration of deep learning models has significantly enhanced prediction accuracy and user experience. This paper introduces a novel model called GRATB, which enhances the existing BERT4Rec framework by incorporating a self-attention mechanism based on time-mixing attention mechanism and dynamic head fusion. Additionally, it introduces a new ’comment tower’ to integrate user review information. By employing a hybrid approach, our model is able to incorporate both the interaction sequence between users and items, as well as sentiment-rich review data. This enables us to obtain a more comprehensive understanding of user preferences. Empirical evidence derived from extensive experimentation demonstrates that GRATB exhibits substantial performance improvements over existing state-of-the-art models across multiple evaluation metrics. GRATB achieves significant enhancements in two critical performance indicators: Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG), with average increases of 2.41% and 3.25%, respectively.

Sequential recommendation aims to predict users’ next interactions based on their historical behavior. However, existing models suffer from three major limitations: (1) reliance solely on collaborative filtering signals while overlooking item semantic information; (2) vulnerability to high-frequency noise in behavior sequences, which interferes with representation learning; and (3) computational inefficiency in Transformer-based bidirectional architectures. To address these challenges, we propose AFNBM (Adaptive Fusion via Noise-filtered Bidirectional Mamba), a novel framework that introduces three key innovations. First, we develop an adaptive semantic-collaborative fusion module that leverages pre-trained language models to extract item semantic embeddings and integrates them with collaborative embeddings through learnable parameters \(\varvec{\alpha }\) and \(\varvec{\beta }\). This mechanism effectively mitigates data sparsity and cold-start problems. Second, we integrate selective frequency modulation (SFM) into a bidirectional Mamba encoder, making this the first work to combine frequency-domain adaptive denoising with state space models (SSMs) for sequential recommendation. The bidirectional encoder captures temporal dependencies in both directions during training while the Mamba blocks themselves maintain linear complexity \(\varvec{O(L)}\). Each Mamba block incorporates an SFM layer with learnable parameter \(\varvec{\gamma }\), enabling adaptive control over high-frequency component retention. The SFM operation introduces an \(\varvec{O(L \log L)}\) factor, making the overall framework complexity \(\varvec{O(L \log L)}\), which remains significantly more efficient than Transformer-based models with \(\varvec{O(L}^{\varvec{2}}\varvec{)}\) complexity while simultaneously improving computational efficiency and noise robustness. Third, we construct a comprehensive end-to-end framework built upon the adaptive fusion and bidirectional Mamba-SFM architecture. For prediction, we employ a gated linear unit (GLU) to selectively enhance salient features, followed by a masked-terminal prediction layer. Extensive experiments validate the effectiveness of our design: ablation studies quantify each component’s contribution (e.g., GLU yields +2.2% to +5.2% gains across datasets), while AFNBM achieves 1.02%-11.76% improvements in Hit@10 and 2.84%-7.57% improvements in NDCG@10 over state-of-the-art baselines across four benchmark datasets, with particularly strong results on sparse and cold-start scenarios.

The traditional machine learning model cannot effectively identify the new network traffic data set, resulting in the model failure. Therefore, in this paper, by analyzing the problems of current network intrusion detection (NID) and combining the application of transfer theory in the detection model, a NID model based on transfer component analysis (TCA) is proposed. Among them, the specific mathematical derivation of the algorithm and the detection process of transfer model are introduced in detail. Then, the classification performance of KNN and SVM based on TCA algorithm for network abnormal traffic is compared. The results show that the TCA algorithm proposed in this paper can effectively improve the accuracy of NID, which is meaningful to expand the application scope of network abnormal traffic detection scheme based on machine learning.