To address the two major challenges in comparative citation generation — determining the comparability between papers accurately and generating comparative sentences， a Comparability Assessment （CA） and comparative citation generation method for scientific papers， named SciCACG（Scientific Comparability Assessment and Citation Generation）， was proposed. Three core modules were constructed in the proposed method： a CA module， which was used to determine whether two papers were comparable； a Comparison object Extraction （CE） module， which was employed to extract specific comparison objects from the papers and references， and a comparative citation generation module， which was responsible for generating the corresponding comparative citation sentences. Firstly， the SciBERT （Scientific BERT） model was used to process the two input papers， and the comparability was assessed through the CA module. Then， for papers determined to be comparable， the CE module was used to identify and extract key comparison objects. Finally， the comparative citation generation module was utilized to generate comparative citations containing these objects. Experimental results show that in the CA stage， the proposed method achieves 0.532 in Mean Reciprocal Rank （MRR） and 0.731 in Recall@10 （R@10）， and outperforms the previous SciBERT-FNN （Scientific Bidirectional Encoder Representations from Transformers-Feedforward Neural Network） method on all the datasets； in the comparative citation generation， Compared to the suboptimal BART-Large （Bidirectional and Auto-Progressive Transformers-Large） method， the F1 scores of ROUGE （Recall-Oriented Understudy for Gisting Evaluation）-1， ROUGE-2， and ROUGE-L in the proposed method have increased by 1.90， 1.29， and 2.55 percentage points， respectively. Additionally， the results confirm that the technologies of automated comparison and analysis of scientific literature are crucial for citation sentence generation tasks； particularly， in enhancing the traceability of comparative information and ensuring the comprehensiveness of citation sentences， these technologies demonstrate substantial practical value.

Air quality data， as a typical spatio-temporal data， exhibits complex multi-scale intrinsic characteristics and has abrupt change problem. Concerning the problem that existing air quality prediction methods perform poorly when dealing with air quality prediction tasks containing large amount of abrupt change， a Multi-Granularity abrupt Change Fitting Network （MACFN） for air quality prediction was proposed. Firstly， multi-granularity feature extraction was first performed on the input data according to the periodicity of air quality data in time. Then， a graph convolution network and a temporal convolution network were used to extract the spatial correlation and temporal dependence of the air quality data， respectively. Finally， to reduce the prediction error， an abrupt change fitting network was designed to adaptively learn the abrupt change part of the data. The proposed network was experimentally evaluated on three real air quality datasets， and the Root Mean Square Error （RMSE） decreased by about 11.6%， 6.3%， and 2.2% respectively， when compared to the Multi-Scale Spatial Temporal Network （MSSTN）. The experimental results show that MACFN can efficiently capture complex spatio-temporal relationships and performs better in the task of predicting air quality that is prone to abrupt change with a large magnitude of variability.

GIFs （Graphics Interchange Formats） are frequently used as responses to posts on social media platforms， but many approaches do not make good use of the GIF tag information on social media when dealing with the question “how to choose an appropriate GIF to reply to a post”. A Multi-Modal Dialog reply retrieval based on Contrast learning and GIF Tag （CoTa-MMD） approach was proposed， by which the tag information was integrated into the retrieval process. Specifically， the tags were used as intermediate variables， the retrieval of text to GIF was then converted to the retrieval of text to GIF tag to GIF. Then the modal representation was learned by a contrastive learning algorithm and the retrieval probability was calculated using a full probability formula. Compared to direct text image retrieval， the introduction of transition tags reduced retrieval difficulties caused by the heterogeneity of different modalities. Experimental results show that the CoTa-MMD model improved the recall sum of the text image retrieval task by 0.33 percentage points and 4.21 percentage points compared to the DSCMR （Deep Supervised Cross-Modal Retrieval） model on PEPE-56 multimodal dialogue dataset and Taiwan multimodal dialogue dataset， respectively.

A Filtered Back-Projection （FBP） ultrasonic tomography reconstruction algorithm based on sparse representation was proposed to solve the difficulty of traditional ultrasonic Lamb wave in detecting and vividly describing the delamination defects composite materials. Firstly， the Lamb wave time-of-flight signals in the composite plate with defect were used as the projection values， the one-dimensional Fourier transform of the projection was equivalent to the two-dimensional Fourier transform of the original image， and the FBP reconstructed image was obtained by convolution with the filter function and projection along different directions. Then， the sparse super-resolution model was constructed and jointly trained by constructing a dictionary of low-resolution image blocks and high-resolution image blocks in order to strengthen the sparse similarity between low- and high-resolution blocks and real image blocks， and a complete dictionary was constructed using low- and high-resolution blocks. Finally， the images obtained by FBP were substituted into the constructed dictionary to obtain the complete high-resolution images. Experimental results show that the proposed algorithm improves Peak Signal-to-Noise Ratio （PSNR）， Structural Similarity （SSIM）， and Edge Structural Similarity （ESSIM） values in the reconstructed image by 9.22%， 2.90%， 80.77%， and 4.75%， 1.52%， 16.5%， respectively compared with the linear interpolation and bicubic spline interpolation algorithms. The proposed algorithm can detect delamination defects in composite materials， improve the resolution of the obtained images with delamination defects and enhance the edge details of the images.

Aiming at the problem of the existing drift detection methods in balancing the detection delay， false positives， false negatives， and spatiotemporal efficiency， a new stage transition threshold parameter was proposed， and a multi-stage weighting mechanism including “stable stage-warning stage-drift stage” was introduced in the concept drift detection to weight the instances in stages， and the mechanism was applied to the double sliding window. Then a Multi-Stage weighted Drift Detection Method （MSDDM） based on Hoeffding inequality was proposed. On artificial datasets， MSDDM detected abrupt and gradual concept drift faster than Fast Hoeffding Drift Detection Method （FHDDM）， Drift Detection Method based on Hoeffding’s bound （HDDM） and other drift detection methods， while maintained a low false detection rate and a false alarm rate. At the same time， MSDDM had the highest classification accuracy in most cases compared with other methods on real-world datasets. Experimental results show that MSDDM can detect concept drift in data streams with high drift detection performance and great spatiotemporal efficiency.

To solve the insufficiency of Stream Control Multiple Access (SCMA) protocol that it fails to consider both the link Quality of Service (QoS) and the channel access scheduling policy of Multiple Input Multiple Output (MIMO) stream, this paper put forward a SCMA/QA protocol. This protocol fully considered the channel states of different streams in each link and built up a discrete Markov chain model based on channel state of stream. Moreover, it took the request of QoS in each link into consideration and adopted fixed Request to Send/Clear to Send (RTS/CTS) to exchange the information of link QoS and taking the link QoS weight as a primary case in link decision, made the link scheduling problem based on QoS of MIMO modeled as an optimization problem, which led to the result of optimal link and the number of communication streams under the Karush-Kuhn-Tucker (KKT) conditions. Finally, according to the numerical analysis which set throughput as the parameter of the QoS, the results show that under the same network environment the SCMA/QA improves the system throughput much better than SCMA and QoS-aware Cooperation SCMA (QCSCMA).

In order to realize the visualization, spatial analysis, automatic modeling and dynamic updating of model, the mine spatial environment and traditional 3D spatial data models were analyzed. Then an entity-oriented spatio-temporal hybrid data model was designed. It integrated the 3D parameter skeleton model, Topology-concerned and Entity-oriented 3D Vector Data Model (TEVDM) and Octree-Block Model (OBM). The TEVDM and OBM were used to express the boundary and internal property of orebodys. The Parametric Entity-Network Data Model (PENDM) was introduced into the model to describe the skeleton of the roadway engineering and production systems. Particularly, a behavior model was introduced into the model to describe the personnel and devices with behavior characteristics. The model also included the complete spatial feature which could describe the set of semantically related entities. Finally, some samples of using this model were given to describe the mines' spatial phenomenon and carry out spatial analysis. The samples show this model has better practicability in mining than traditional models.

In view of the characteristics of cable channel, a joint design of adaptive equalizer and carrier recovery loop for high order QAM signals was proposed, which was suitable for ITU-T J.83 standard. The equalizer initially operated in Constant Modulus Algorithm (CMA) mode to compensate the channel distortion. When the eye diagram was opened, the equalizer switched to Least Mean Square (LMS) mode to decrease the Mean Square Error (MSE). For high order QAM signals, the carrier recovery loop initially operated in Polarity Decision Algorithm (PDA) under fast and slow modes which were set in Loop Filter (LPF) to capture the frequency offset. When the frequency offset was captured, the loop switched to Decision Direct Algorithm (DDA) to decrease the phase jitter. The simulation studies show the good performances of this design. The whole design was synthesized under Altera Stratix Ⅱ EP2S130F1020C5 FPGA. Highest clock frequency after being routed reached as high as 90.47MHz.

Aiming at the problem of big distortion caused by using the traditional blind 3D watermarking algorithm under the same restriction of robustness, a self-adaptive blind 3D model watermarking algorithm based on surface roughness was proposed. The idea of visual masking was introduced into the algorithm, and the vertex which was waiting for embedding was chosen by their surface roughness and location, which let the intensity of embedded watermarking self-adapted to the surface roughness of the model. The experimental results show that the proposed algorithm can reduce the distortion efficiently under the condition of keeping the restriction on robustness.