In view of the high cost of controlling all the nodes in the traffic network, a pinning control framework for urban traffic network analysis and control network in the case of limited resources were constructed by this paper, and a new pinning control algorithm for urban traffic network was proposed.By using the mutual coupling and containment relationship between nodes and controlling some key nodes in the road network, the expected behavior of the whole network was guaranteed, and the limitation that the system consumes too much computing and control resources were effectively solved.The control input was set as the variation of the duration of the green light, a new pinning controller was designed, and the conditions for effectively ensuring the stability of the urban road traffic network are proposed.Through the simulation analysis, the signal control method proposed can make the urban road traffic network achieve the desired state, and effectively improve the utilization of road resources in the case of limited infrastructure and control costs.

To address the issues of incomplete feature extraction, poor stability, and limited generalization in traditional fault diagnosis models, a model based on a multi-scale convolutional neural networks (MCNN), bidirectional gated recurrent units (BiGRU), and multi-head self-attention mechanism (MSA) was proposed. The model was designed to achieve comprehensive feature extraction from both spatial and temporal perspectives. It took raw vibration signals as input, and multi-scale features were extracted through convolution kernels of different sizes. A multi-head self-attention mechanism was used to dynamically adjust output weights, disregarding redundant information and weighting the extracted features for fusion. Then the fused features were input into a BiGRU network, which utilized a bidirectional information fusion mechanism to explore information from both past and future directions, capturing dependencies between different parts of the input sequence. Finally, Softmax was employed for classification. Experimental validation was conducted using three bearing fault datasets, and the results show that the proposed model has excellent performance metrics on different datasets and showcases good generalization and feasibility.

In order to investigate the role of rheumatoid arthritis (RA)-related pathways in lung squamous cell carcinoma (LSCC). By obtaining gene expression data for RA and LSCC from the GEO and TCGA database, differentially expressed genes were screened using GEO2R tool and Rstudio software. GO/KEGG functional enrichment analysis identified key genes in the RA signaling pathway. Combining SNP data from the IEUopenGWAS database, Mendelian randomization analysis was used to assess the causal relationship between the RA signaling pathway and LSCC. The constructed gene-drug and ceRNA networks, along with immune cell infiltration analysis, revealed 188 co-expressed differential genes, mainly enriched in the RA signaling pathway. Mendelian randomization analysis showed that increased activity of the RA signaling pathway is associated with a reduced risk of LSCC. This study provides new insights into the pathogenesis and potential research directions for the treatment of LSCC.

Compressed air energy storage, as a new energy storage technology, plays an important role in peak shaving and valley filling. Based on the compressed air energy storage with abandoned oil wellbores, a pipeline-wellbore gas storage chamber, that is, the storage space was composed of above ground pipelines and underground wellbores, was proposed. Its inflation process was simulated, with a focus on analyzing the thermodynamics and flow characteristics of the internal gas. The results showed that with compressed gas flowed into the pipeline wellbore gas storage chamber, the gas temperature rapidly increased under the heating effect of the high-temperature wellbore wall. Subsequently, the temperature of the gas became slightly higher than that of the wall, at this point, a heat release of the gas to the wall. The gas temperature and heat dissipation tended to remain stable until the gas storage pressure rose to about 3 MPa. Due to the presence of geothermal gradient, there were significant differences in gas characteristics in different areas of the underground wellbore during the inflation process. As the depth of the wellbore increased, gas flow rate, density, and frictional resistance decreased. With the increase of the gas storage pressure, the differences in the gas flow rate and frictional resistance in different areas diminished. The results of this study provide significant theoretical insights that can effectively inform the practical application of compressed air energy storage systems, particularly those that employ underground wellbores as the repository for gas storage.

To tackle the computational cost and registration time challenges in traditional point cloud registration methods like ICP (iterative closest point) such as LIO-SAM (tightly-coupled lidar inertial odometry via smoothing and mapping) and newer models utilizing deep neural networks such as HRegNet(hierarchical registration network), a lightweight and real-time HKRNet (hierarchical kcpstack registration network) network model was proposed. The model was developed by thoroughly studying the HRegNet neural network point cloud registration framework. Initially, a combined filtering approach involving point cloud voxelization and Gaussian threshold downsampling was used to remove redundant points from ground radar scans, reducing the point count from around 130 000 to about 70 000. Subsequently, the computationally intense KNN (K-nearest neighbors) point cloud clustering algorithm within the HRegNet model was enhanced by optimizing it to a KD-Tree (K-dimensional tree) algorithm, resulting in a 25% improvement in processing speed while upholding accuracy. Lastly, to address high memory usage and low computational efficiency of the convolutional modules in the model, a lightweight convolutional module leveraging tensor decomposition and a hierarchical singular value decomposition algorithm was introduced. This leaded to a compressed model size of 86.1% of the original and a decrease of 61.2% in computational cost. The outcomes indicate that the HKRNet network, in comparison to the HRegNet network, can reduce registration time by 40% with minimal loss of accuracy, achieving a single registration time not exceeding 84ms, thus meeting real-time registration requirements.

Seasonal segmentation of building electricity consumption time series (BECTS) is of great significance for accurate load forecasting and pattern mining. Aiming at the problem that accurate BECTS seasonal segmentation is difficult to be realized by traditional timing segmentation, fixed-temperature segmentation and adaptive five-days temperature segmentation methods, a new adaptive seasonal segmentation method for BECTS based on Toeplitz inversed covariance-based clustering (TICC) was proposed. The method was based on the binary time series of building hourly electricity load and outdoor dry bulb temperature, and the TICC algorithm was used for real-time segmentation and clustering. A large public building electricity load case in a hot summer and warm winter area was analyzed, and the result showed that the similarity between samples of the same type and the difference between samples of different types were enhanced by the method. Compared with the timing segmentation, fixed-temperature segmentation and adaptive five-days temperature segmentation methods, the average dynamic time warping (DTW) distance of each category after TICC segmentation was improved respectively by 46.54%, 35.73% and 7.59%. This method can be used as data preprocessing to provide data support for single building data mining analysis, such as building electricity consumption pattern mining and load forecasting.

Existing methods for audio-visual cross-modal association learning often adopt a dual-stream network structure, but they still face challenges in reducing computational complexity, model light weighting, and efficient feature fusion. To improve model performance and enhance the efficiency of cross-modal learning, a single-stream network-based approach for audio-visual cross-modal learning was proposed. Firstly, preprocessed data from both modalities were fed into a single-stream feature extraction network, where a class-information-based loss function was employed to learn and extract feature vectors from both modalities. Subsequently, attention-based feature fusion was performed on the extracted feature vectors from both modalities. Finally, a combination of cosine similarity algorithm and cross-entropy loss was used to learn the association between the two modalities, thus completing the cross-modal association learning task. Experimental results demonstrate that the proposed method achieves promising performance in audio-visual cross-modal verification, matching, and retrieval tasks, ensuring excellent performance while considering the lightness and flexibility of the network structure.

In order to address the issues of incomplete collection, vulnerability to attacks, and limitations in specific recognition scenarios in single modal biometric information, a multi-level fusion recognition model for faces and iris was proposed, a multi-modal biometric recognition system was designed and implemented to integrate the proposed model in a modular manner. The lightweight convolutional neural networks was used as feature extractors, intra class correlations between different modal features was utilized on the feature level, normalizing and concatenating the features of different modalities. The minimum strategy was used to fuse left and right iris scores on the score layer, the average strategy was used to fuse iris scores and face scores. Homologous multi-modal datasets was extracted from the CASIA-IrisV4-Distance dataset for experiment verification, feature layer fusion algorithm and score layer fusion algorithm both achieves an accuracy of 99.8%. It is observed in the experiment that this system has robustness and generalization.

Addressing the limitation of existing sequence labeling approaches in effectively recognizing nested entities within Chinese electronic health records (EHRs), a novel named entity recognition model that integrates MacBERT and a global pointer network was proposed. Initially, the MacBERT-large pre-trained model transformed the text into context-sensitive dynamic vectors. Subsequently, the fast gradient method (FGM) was employed to generate adversarial samples, which were incorporated into the original vectors and fed into a BiLSTM (bi-directional long short-term memory) network to capture contextual features. To enhance the capture of long-distance semantic features, an attention mechanism was introduced. Finally, a global pointer network model was leveraged to decode simultaneously considering both head and tail feature information, thereby achieving superior prediction performance for medical nested entities. Experimental results demonstrate that compared to the state-of-the-art global pointer model, the proposed model achieves an improvement of 1.8%, 1.37%, and 1.72% in F₁-score on the CCKS2019 dataset and two versions of the CMeEE Chinese EHR dataset, respectively, validating the effectiveness of the proposed approach.

Aiming at obvious load fluctuation trend, strong randomness and low accuracy caused by unreasonable parameter values of the prediction model involved into the power load forecasting process, a combined prediction model composing of ALIF (adaptive local iterative filtering), VMD (variational mode decomposition), NGO (northern goshawk optimization) and CNN-LSTM (convolutional neural networks - long short-term memory) was established. Firstly, CCM (convergent cross-mapping) method was used to identify the key factors affecting the power load. Secondly, an innovative combination of ALIF, NGO-based VMD and FE (fuzzy entropy) was employed for combinatorial decomposition and necessary recombination of original load sequence. Next, based on the modal components generated after decomposition and recombination, combined with optimal hyperparameter combination of CNN-LSTM determined by NGO method, an NGO-CNN-LSTM day-ahead power load combination prediction model with the high prediction accuracy, short training time and fast convergence speed was formulated. Compared with other benchmark models, the obtained results demonstrated that the proposed model has the better adaptability and prediction accuracy, and can provide important technical support for the safe, reliable and economical operation of power system.