2025 Vol.43

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Journal of Applied Sciences    2025, 43 (1): 0-0.   Abstract （93）      PDF（pc） （81KB）（46）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Disease Prediction via Capsule Network and Causal Reasoning SUN Mingchen, JIN Hui, WANG Ying Journal of Applied Sciences    2025, 43 (1): 1-19.   DOI: 10.3969/j.issn.0255-8297.2025.01.001 Abstract （181）      PDF（pc） （2777KB）（69）       Knowledge map    Save Existing deep learning-based disease prediction models are predominantly datadriven, leading to a high dependency on the sample size and the coverage of disease types in the training dataset. The current methods for disease prediction have the following limitations: 1) When the model is trained on a limited range of disease types, its performance deteriorates significantly and may produce incorrect predictions for rare diseases. 2) The training data may contain features that are irrelevant or have weak correlations with the prediction target. This noise may prevent the model from making stable and reliable predictions, thus failing to meet the practical needs of high safety and reliability required in medical applications. To address these issues, this paper proposes a disease prediction model named CausalCap, which integrates capsule networks with causal inference. Specifically, we obtain the causal effects and relationships between clinical features and disease labels, and construct a causal graph of clinical features. The causal graph is then pruned to delete false nodes with no causal relationships to the disease labels, only retaining key nodes that truly influence the occurrence of the disease, resulting in a refined disease causal graph. Finally, hierarchical graph capsule neural network (HGCN) classifies the disease causal graph for disease prediction. Extensive evaluations on six public datasets demonstrate that CausalCap achieves an average improvement of 2.50% in ACC and 6.46% in F1 metrics compared to the suboptimal methods. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2025, 43 (1): 2-0.   Abstract （66）      PDF（pc） （46KB）（21）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Entity Relationship Extraction Framework Based on Pre-trained Large Language Model and Its Application WEI Wei, JIN Chenggong, YANG Long, ZHOU Mo, MENG Xiangzhu, FENG Hui Journal of Applied Sciences    2025, 43 (1): 20-34.   DOI: 10.3969/j.issn.0255-8297.2025.01.002 Abstract （245）      PDF（pc） （1446KB）（251）       Knowledge map    Save Entity relationship extraction is a crucial foundation for building large-scale knowledge graphs and domain-specific datasets. This paper proposes an entity relationship extraction framework based on pre-trained large language models (PLLM-RE) for relation extraction in circular economy policies. Within this framework, entity recognition of circular economy policy texts is performed based on the model RoBERTa. Subsequently, the bidirectional encoder representation from Transformers (BERT) is employed for entity relation extraction, facilitating the construction of a knowledge graph in the field of circular economic policies. Experimental results demonstrate the framework outperforms the baseline models including BiLSTM-ATT, PCNN, BERT and ALBERT in task of entity relationship extraction for circular economy policies. These findings validate the adaptability and superiority of the proposed framework, providing new ideas for information mining and policy analysis in the field of circular economy resources in the future. Reference | Related Articles | Metrics | Comments（0）

Select

Avalanche Prediction and Prevention Strategies Integrating Machine Learning and Dynamic Model Optimization JIN Yongchao, WANG Zhijian, JIA Huishuang, DU Yuntian, HU Xinting, CHEN Xuebin Journal of Applied Sciences    2025, 43 (1): 35-50.   DOI: 10.3969/j.issn.0255-8297.2025.01.003 Abstract （150）      PDF（pc） （4878KB）（59）       Knowledge map    Save Blasting is an effective method to prevent avalanches, but it is difficult to determine the appropriate blasting time, blasting location and blasting energy. This study began by collecting and preprocessing indicator data about avalanches. Then we conducted exploratory data analysis on the data, and found a strong seasonal pattern in avalanche occurrences. Using 80% of the data as the training set and 20% as the test set, the support vector machine, random forest and perceptron neural network models were established, with parameters optimized using the Bayesian optimization algorithm. The results showed that the perceptron neural network achieved the highest accuracy. Subsequently, the three models were integrated according to the loss degree, and three integration strategies were compared. The results showed that the highest accuracy of the SVM-RF-MLP model was 0.952. A basic blasting energy model was then developed, taking into account the changes in mountain height and snow layer density over time. Using historical data, a dynamic avalanche stability blasting energy model was built to identify the distribution patterns in snow layer stability. The data is simulated and verified, and a three-dimensional mountain visualization analysis is performed to obtain the optimal blasting timing, blasting location and blasting energy. Reference | Related Articles | Metrics | Comments（0）

Select

Improved Daily Average 2 m Temperature Correction Method Based on U-Net WANG Binglun, FANG Wei Journal of Applied Sciences    2025, 43 (1): 51-65.   DOI: 10.3969/j.issn.0255-8297.2025.01.004 Abstract （90）      PDF（pc） （13115KB）（31）       Knowledge map    Save In response to the limitations of the widely utilized deep learning model U-Net, which is unable to adequately learn spatial features and suffers from the loss of image detail information, the S-CUnet 3+ model has been proposed. S-CUnet 3+ enhances U-Net in two ways: firstly, it integrates the original model with the Swin Transformer, enabling it to learn global features of images, and secondly, it introduces multi-scale connection operations. The model also adopts pre-training and fine-tuning strategies to correct multiple forecast lead times simultaneously. Experimental results of correcting daily average 2 m temperature forecasts across seven lead times show that the S-CUnet 3+ model has a significant correction effect for all lead times, with the best correction effect at the 24-hour lead time. The mean absolute error and root mean square error are reduced by 50.64% and 49.25%, respectively. Moreover, S-CUnet 3+ outperforms seven existing correction methods: anomaly numerical-correction with observations, quantile regression, ridge regression, U-Net, CU-Net, Dense-CUnet, and RA-UNet. Reference | Related Articles | Metrics | Comments（0）

Select

A Semantic Segmentation Network Based on Lightweight Convolutional Modules LIAN Xiaofeng, KANG Maomao, TAN Li, WANG Yanli Journal of Applied Sciences    2025, 43 (1): 66-79.   DOI: 10.3969/j.issn.0255-8297.2025.01.005 Abstract （127）      PDF（pc） （5717KB）（107）       Knowledge map    Save Semantic simultaneous localization and mapping augmented with deep learning provides an effective solution for handling dynamic scenes. However, this technology still faces challenges of high computational resource consumption and model complexity. To address these issues, this paper proposes a lightweight semantic segmentation network based on improvements to BlendMask. Firstly, a lightweight Ghost-depthwise separable convolution with efficient channel attention block (GDS-ECA) module is designed. This module replaces a few convolution operations in Ghost convolution with depthwise separable convolution to reduce parameters and computational load, while incorporating an attention mechanism to enhance feature representation capabilities. Secondly, a bottleneck GDS-ECA attention transformer network (BGTNet) is proposed, which applies GDS-ECA convolution to the neck module’s convolution layers to improve feature extraction precision. Additionally, traditional convolutions in the feature pyramid network (FPN) are replaced with GDS-ECA convolutions, creating a lightweight FPN (L-FPN). Combined with BGTNet, this forms the Backbone of the proposed semantic segmentation network. Finally, experiments on the COCO dataset validate the improvements, demonstrating a 7.3 ms reduction in processing time per image, and a 1.5% improvement in average precision. Reference | Related Articles | Metrics | Comments（0）

Select

Lightweight and Efficient Image Steganography Based on Convolutional Neural Network DUAN Xintao, BAI Luwei, XU Kaiou, ZHANG Meng, BAO Mengru, WU Yinhang, QIN Chuan Journal of Applied Sciences    2025, 43 (1): 80-93.   DOI: 10.3969/j.issn.0255-8297.2025.01.006 Abstract （144）      PDF（pc） （11678KB）（38）       Knowledge map    Save Deep learning-based image steganography often faces challenges due to the large number of model parameters and high computational demands. In response, a lightweight and efficient image steganography method is proposed. Firstly Ghost module is introduced into the encoder and decoder, which reduces the number of parameters and computational complexity. Furthermore, a multi-scale feature fusion module is designed to capture complex relationships within multidimensional data. In addition, a novel hybrid loss function is proposed, which can improve image steganography quality without modifying the model. Experimental results show that the proposed method achieves a peak signal-to-noise ratio (PSNR) of 47.59 dB on a 256×256 pixel image. Compared with the current best image steganography method, the steganography quality is improved by 1.7 dB, the number of parameters is reduced by 77%, and number of computations by 91%. These results confirm that the proposed method effectively enhances steganography quality with reduced number of parameters and computational complexity of the model, achieving a lightweight and efficient model. Reference | Related Articles | Metrics | Comments（0）

Select

Lightweight Fault Diagnosis Model Based on Parallel Optimized CBAM JIA Zhiyang, XU Zhao, LENG Yanmei, WEN Xin, GONG Haoyu Journal of Applied Sciences    2025, 43 (1): 94-109.   DOI: 10.3969/j.issn.0255-8297.2025.01.007 Abstract （135）      PDF（pc） （6520KB）（67）       Knowledge map    Save In engineering practice, the performance of fault diagnosis models is affected by factors such as strong noise interference, limited sample sizes, and high model complexity, which poses challenges to the application of existing data-driven intelligent models for equipment diagnosis. To address these issues, this paper proposes a lightweight model, PCSA-Net, based on a parallel optimized convolutional block attention module (CBAM). First, a multi-scale signal feature extractor (SFE) is used to convert the input sensor signal into a feature map. Then, the traditional CBAM is optimized through the development of a collaborative attention block, the design of a learnable layer scaling strategy, and the parallelization of perceptual data features. Additionally, a PW-Pool dimension reduction module is introduced by combining point convolution with average pooling layers to reduce the number of model parameters. The channel feature vector of the feature map is then integrated to obtain the final diagnosis result. Finally, the proposed model is validated using two datasets containing common bearing faults. Experimental results show that in the small sample bearing fault diagnosis (BFD) task, the proposed model outperforms the existing mainstream fault diagnosis framework in terms of lightness and robustness, and meets the practical needs of bearing fault detection in real-world applications. Reference | Related Articles | Metrics | Comments（0）

Select

Recommendation Algorithm Based on Relative Trust Enhancement CHENG Jiayi, CHEN Lingjiao, WU Yuezhong Journal of Applied Sciences    2025, 43 (1): 110-122.   DOI: 10.3969/j.issn.0255-8297.2025.01.008 Abstract （104）      PDF（pc） （751KB）（23）       Knowledge map    Save Socialized recommendation has become one of the hot research topics in recent years. Introducing users’ social relationships into the recommendation algorithm based on their historical behavior can alleviate the problems of data sparsity and cold start faced by recommendation systems. This paper proposes a relative trust enhancement recommendation algorithm based on the CosRA (RTECosRA). In the bipartite “user-object” network, this algorithm allocates resources based on the CosRA similarity index and introduces users’ trust relationships during the resource allocation process. It adjusts the resource values obtained by trusted users, thereby increasing the recommendation rate of the items selected by trusted users. The results on the FriendFeed and Epinions datasets show that compared with the baseline algorithms, the RTECosRA algorithm has improvements in both accuracy and diversity. Moreover, by incorporating trust relationships, it expands the recommendable range for users and alleviates the cold start problem to a certain extent. Reference | Related Articles | Metrics | Comments（0）

Select

A Diffusion Map Recommendation Model Based on Multi-hop Mechanism LIU Jianing, ZHANG Sijia, ZHANG Zhenglong, WANG Yihan, AN Zongshi Journal of Applied Sciences    2025, 43 (1): 123-136.   DOI: 10.3969/j.issn.0255-8297.2025.01.009 Abstract （117）      PDF（pc） （1273KB）（52）       Knowledge map    Save To address the challenges of high-order modeling and insufficient user feature modeling in knowledge graph-based recommendation systems, a diffusion map recommendation model based on multi-hop mechanism (MultiHop-GDN) is proposed. This model mines high-order semantic information from the knowledge graph through an end-to-end method, covering three parts: knowledge graph construction, feature extraction network design and multi-hop diffusion model development. The knowledge graph is constructed using user and project attributes, enabling in-depth analysis of information such as user interests, preferences, and historical behaviors to build user portraits and interest models. A feature extraction network is introduced to capture deep semantic information and obtain prediction values through the calculation of this model. Comparative experiments on two public datasets show that MultiHop-GDN effectively achieves high-level modeling of both users and projects, outperforming other representative models in recommendation effects. Reference | Related Articles | Metrics | Comments（0）

Select

Video-Based Facial Feature Computation Methods WANG Yingxiao, YANG Yanhong, TAN Yunfeng Journal of Applied Sciences    2025, 43 (1): 137-153.   DOI: 10.3969/j.issn.0255-8297.2025.01.010 Abstract （136）      PDF（pc） （730KB）（177）       Knowledge map    Save This paper presents a review of research in video face recognition conducted over the past five years. It provides a comparative analysis of the facial feature computation methods, categorizing them into traditional approaches, deep learning techniques, and feature aggregation/fusion methods. Traditional feature extraction methods include linear and nonlinear approaches, while deep learning methods include spatial and temporal feature extraction techniques. Feature aggregation and fusion methods integrate multiple feature sources and fuse features from different time periods to improve recognition performance. At the end of each subsection, this paper also provides a unified analysis of the algorithms used in the literature, highlighting their advantages, evaluation metrics, and applications. Through this research, we aim to provide more reliable and efficient solutions for practical applications of video face recognition systems and promote further advancements in this field. Reference | Related Articles | Metrics | Comments（0）

Select

Bird Action Recognition Based on Multiple Excitation and Pyramid Split Attention DENG Shuchong, CHEN Aibin, DAI Zijian Journal of Applied Sciences    2025, 43 (1): 154-168.   DOI: 10.3969/j.issn.0255-8297.2025.01.011 Abstract （99）      PDF（pc） （7521KB）（35）       Knowledge map    Save Aiming at the problem of low recognition accuracy and high misclassification rate of traditional action recognition methods in dealing with complex bird action patterns, an enhanced deep learning model is proposed. The model integrates a multiple-excitation module and pyramid split attention to improve 3D residual networks, aiming to improve both the accuracy and efficiency of bird action recognition. The inter-frame difference method is utilized to effectively reduce the computational burden while preserving critical spatio-temporal information, thereby improving the recognition accuracy. The introduction of a multiple-excitation module improves the original residual block so that the model can accurately capture subtle motion action features, which solves ambiguities in recognizing complex dynamic actions of birds. Additionally, the original 3D convolutional layer is replaced with 3D pyramid split attention to achieve effective capture of bird action features at different scales. Experiments conducted on a self-built bird action video dataset demonstrate a high recognition accuracy of 90.48%, which significantly outperforms the baseline model and other existing popular action recognition networks. These results confirm that the model can effectively handle the complex bird action recognition task. Reference | Related Articles | Metrics | Comments（0）

Select

Benchmarking of Spiking Neural Networks and Performance Evaluation of Neuromorphic Training Frameworks HU Wangxin, CHENG Yingchao, HE Yulin, HUANG Zhexue, CAI Zhanchuan Journal of Applied Sciences    2025, 43 (1): 169-182.   DOI: 10.3969/j.issn.0255-8297.2025.01.012 Abstract （133）      PDF（pc） （805KB）（145）       Knowledge map    Save With the growing interest in spiking neural networks (SNNs), the development of open-source neuromorphic training frameworks has also accelerated. However, there is currently a lack of systematic guidelines for selecting these frameworks. To address this issue, this paper proposes a benchmarking method for SNNs based on image classification tasks. This method designs a convolutional neural network and a fully connected deep neural networks to evaluate two SNN training approaches: direct training with surrogate gradient backpropagation and conversion from artificial neural networks (ANNs) to SNNs. Based on the MNIST, Fashion-MNIST, and CIFAR-10 benchmark image datasets, the performance comparisons of various neuromorphic training frameworks are conducted using evaluation metrics such as training time and classification accuracy. Experimental results indicate that the neuromorphic training framework SpikingJelly outperforms others in terms of both training time and classification accuracy in direct SNN training, while the Lava framework achieves the highest classification accuracy in ANN-to-SNN conversion training. Reference | Related Articles | Metrics | Comments（0）

Select

An Exponential Moving Average-Based Mechanism for IoT Edge Device Selection WU Tong, YUAN Peiyan Journal of Applied Sciences    2025, 43 (1): 183-194.   DOI: 10.3969/j.issn.0255-8297.2025.01.013 Abstract （87）      PDF（pc） （1416KB）（25）       Knowledge map    Save In small cell networks, the number of user equipment (UE) often exceeds the number of small base stations (SBS), with each SBS capable of serving multiple UE and each UE covered by multiple SBS. It is a significant challenge to decide the optimal SBS to serve each UE in small cell networks. Traditional coordinated multiple point (CoMP) operations, which allocate resources based on proportionate fairness, fail to consider the dynamic nature of the system, leading to suboptimal resource utilization. Therefore, this paper proposes a CoMP operation method based on exponential moving average (EMA). The proposed method prioritizes all UE and SBS at each time slot and increases the allocation weight for devices with high priority in the next time slot, enabling high-weight UE to receive services from more SBS and ultimately achieving dynamic resource adjustment. Experimental results demonstrate that the EMA-based CoMP operation significantly enhances system peak time and overall throughput efficiency while reducing the system’s dropout rate. Furthermore, it provides a better device selection mechanism for the internet of things edge system. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2025, 43 (2): 0-0.   Abstract （39）      PDF（pc） （77KB）（23）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2025, 43 (2): 1-0.   Abstract （23）      PDF（pc） （46KB）（5）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Correctness Verification for Interactive Smart Contracts at Runtime WANG Jiacheng, JIANG Jiajia, LI Dan, ZHANG Yushu Journal of Applied Sciences    2025, 43 (2): 195-207.   DOI: 10.3969/j.issn.0255-8297.2025.02.001 Abstract （57）      PDF（pc） （706KB）（41）       Knowledge map    Save Compared with a single smart contract, interactive smart contracts have more complex interactions such as mutual calling. However, existing smart contract detection and verification methods primarily consider the problems existing in a single smart contract, and the correctness of interactive smart contracts cannot be guaranteed. To address this limitation, this paper proposes a method for verifying the correctness of interactive smart contracts, where behavior interaction priority (BIP) modeling is built for interactive smart contract systems and Solidity deployment diagram (SDD) is introduced to describe contract interactions. By employing formal verification techniques, the proposed approach ensures the correctness of the interactive smart contracts and realizes their reconstruction. Experimental results show that the proposed method can effectively verify the correctness of interactive contract systems. Reference | Related Articles | Metrics | Comments（0）

Select

3D Trajectory Optimization and Resource Allocation in UAV-Assisted NOMA Communication Systems ZHU Yaohui, WANG Tao, PENG Zhenchun, LIU Han Journal of Applied Sciences    2025, 43 (2): 208-221.   DOI: 10.3969/j.issn.0255-8297.2025.02.002 Abstract （58）      PDF（pc） （2349KB）（20）       Knowledge map    Save UAV-assisted communication system is an important component of future wireless networks. In order to further improve the utilization of time-frequency resources in UAV-assisted communication systems, this paper proposes a communication architecture based on non-orthogonal multiple access (NOMA) technology and introduces a TD3-TOPATM (twin delayed-trajectory optimization and power allocation for total throughput maximization) algorithm based on the double-delay deep deterministic policy gradient strategy. The TD3-TOPATM algorithm jointly optimizes the 3D trajectory and power allocation strategy of the UAV, with the aim of maximizing the total throughput while satisfying constraints on maximum power, spatial boundaries maximum flight speed, and quality of service (QoS). Simulation results show that compared with the trajectory optimization algorithm with random optimization, the TD3-TOPATM algorithm achieves a performance gain of 98%. Additionally, it outperforms the deep Q-network (DQN)-based trajectory optimization and resource allocation algorithm, increasing total throughput by 19.4%, and surpasses the deep deterministic policy gradient (DDPG)-based algorithm with a 9.7% throughput gain. Furthermore, the NOMA-based UAV-assisted communication scheme achieves a 55% performance gain compared to the OMA-based scheme. Reference | Related Articles | Metrics | Comments（0）

Select

A Movie Rating Prediction Model Leveraging User Profile Similarity AI Jun, LI Minghao, SU Zhan Journal of Applied Sciences    2025, 43 (2): 222-233.   DOI: 10.3969/j.issn.0255-8297.2025.02.003 Abstract （48）      PDF（pc） （2419KB）（15）       Knowledge map    Save Collaborative filtering algorithms are widely used in recommendation systems, with a key research focus on how to achieve effective user clustering and identify more accurate sets of similar neighbors. One of the key research focuses is to achieve user clustering and identify more similar neighbor sets. To enhance the accuracy of classification and prediction in these algorithms, this paper proposes a movie recommendation algorithm based on user profile similarity. First, based on a tag set of movie content features, a user preference profile matrix is constructed by calculating the frequency of user ratings among different movie content tags. Then, user similarity is calculated through this matrix, and a user complex network is modeled to determine the centrality weight of users within the network. Finally, the community weight is obtained through K-core decomposition of the user network. The rating predictions are improved by integrating the centrality weight and community weight of neighboring users. Experimental results show that the proposed algorithm improves prediction accuracy and classification accuracy by 2.72% and 3.17%, respectively. These results validate the effectiveness of complex network modeling based on user profile similarity for enhancing information utilization in recommendation systems. Reference | Related Articles | Metrics | Comments（0）

Select

Video Anomaly Detection Method Based on Multi-scale Feature Fusion and Attention Mechanism WU Xiang, XIAO Jian, JI Genlin Journal of Applied Sciences    2025, 43 (2): 234-244.   DOI: 10.3969/j.issn.0255-8297.2025.02.004 Abstract （53）      PDF（pc） （851KB）（14）       Knowledge map    Save Motion objects in video frames often exhibit diverse scales over time, which poses a challenge for video anomaly detection. Although traditional generative adversarial networks (GANs) have achieved some success in video anomaly detection tasks, their performance is limited due to the use of a single-scale feature extraction that fails to capture features of objects at different scales. To address this issue, this paper proposes a video anomaly detection method based on a GAN structure that incorporates multi-scale feature fusion and attention mechanisms. Specifically, different-sized convolutional kernels are employed to capture features with varying receptive fields, which are then fused to obtain multi-scale feature representations. Additionally, a coordinate attention mechanism is introduced after the transposed convolutional layers of the generator, allowing adaptive allocation of feature map weights to enhance the model’s perception of crucial features.Experimental results on the public datasets UCSD Ped2 and Avenue demonstrate that the proposed method outperforms existing approaches. Reference | Related Articles | Metrics | Comments（0）

Select

Low-Light Image Enhancement Based on Dark Region Guidance WANG Wanling, XIONG Bangshu, OU Qiaofeng, YU Lei, RAO Zhibo Journal of Applied Sciences    2025, 43 (2): 245-256.   DOI: 10.3969/j.issn.0255-8297.2025.02.005 Abstract （42）      PDF（pc） （21823KB）（12）       Knowledge map    Save To address the issues of overexposure, color distortion and detail loss in existing enhancement methods when image illumination distribution is uneven, a low-light image enhancement method combining dark region guidance and attention mechanism is proposed. Firstly, the simple linear iterative clustering (SLIC) method is used to generate a dark region guidance map, which guides the network to enhance the underexposed regions of the image while ensuring that the normally exposed regions are not overexposed. Secondly, a channel attention module is designed to improve the extraction of color information, effectively restoring the image color while maintaining natural color fidelity. Subsequently, a global context module is established to enhance the network’s global perception capability, enriching image details. Finally, an enhancement network is designed to fuse the input features with the output features of the dark area attention network,achieving contrast re-enhancement. Multiple comparative experiments are conducted on six public datasets to compare the performance from both subjective and objective aspects. It is shown that the proposed method effectively solves the problems of color distortion, detail loss and uneven exposure in low-light images, delivering superior visual enhancement effect and generalizability. Reference | Related Articles | Metrics | Comments（0）

Select

Interference Analysis and Optimal Window Design for Windowed UFMC Systems XIE Yu, WEN Jiangang, NI Zhengwei, HUA Jingyu Journal of Applied Sciences    2025, 43 (2): 257-273.   DOI: 10.3969/j.issn.0255-8297.2025.02.006 Abstract （47）      PDF（pc） （913KB）（11）       Knowledge map    Save In this paper, we first investigate the signal and interference characteristics of the windowed universal filtered multi-carrier (UFMC) system in presence of carrier frequency offset (CFO), and then derive the expression of subcarrier signal-to-interferenceplus-noise ratio (SINR). Based on the relationship between symbol error rate (SER) and SINR, an optimization model for window design is formulated to maximize the geometric mean of subcarrier SINR. The successive convex approximation (SCA) algorithm is then employed to solve the optimization problem and determine the optimal window. Finally, SER simulations with various window functions demonstrate that the windowed operations effectively reduce the UFMC interference caused by CFO. Moreover, compared with traditional window functions, the proposed optimal window function significantly improves the system SER, and behaves reliably across a wide signal to noise ratio range. Reference | Related Articles | Metrics | Comments（0）

Select

Hybrid Memetic Algorithm for Soft-Clustered Capacitated Arc Routing Problem KOU Yawen, ZHOU Yangming, WANG Zhe Journal of Applied Sciences    2025, 43 (2): 274-287.   DOI: 10.3969/j.issn.0255-8297.2025.02.007 Abstract （38）      PDF（pc） （683KB）（5）       Knowledge map    Save The soft-clustered capacitated arc routing problem (SoftCluCARP) is an extension of the classical capacitated arc routing problem. Due to its NP-hard nature, solving it is computationally challenging. In this work, we propose an effective hybrid memetic algorithm (HMA) to solve SoftCluCARP. HMA integrates three distinct algorithm modules: a group matching-based crossover to produce promising offspring solutions, a two-stage variable neighborhood search to perform local optimization, and a quality-and-distance population updating to maintain a high-quality population. Experimental results show that HMA is highly competitive compared to the existing exact algorithm in terms of both solution quality and computation time. Reference | Related Articles | Metrics | Comments（0）

Select

Expert Relearning Reasoning Question Answering Method Based on Knowledge Graph and Gating Mechanism FANG Xiao, WANG Hongbin Journal of Applied Sciences    2025, 43 (2): 288-300.   DOI: 10.3969/j.issn.0255-8297.2025.02.008 Abstract （38）      PDF（pc） （700KB）（18）       Knowledge map    Save Existing graph neural network (GNN)-based question answering (QA) methods using pre-trained language models and knowledge graphs mainly focus on building knowledge graph subgraphs and reasoning processes. However, such methods ignore the semantic differences between question context and knowledge graphs, limiting their ability to deeply mine text representations. Moreover, they fail to comprehensively consider the varying contributions of these two representations to answer prediction. To address these challenges, this paper proposes an expert relearning reasoning QA method based on knowledge graphs and a gating mechanism. This method splices and fuses the question context representation with the inferred knowledge graph representation, and randomly assigns the fused representation vector to the expert network to relearn the entity semantic features associated with the question context and knowledge graph. By mining deeper hidden knowledge and incorporating the gating mechanism, the model accurately scores the question context and the inferred knowledge graph representation, dynamically adjusting their contribution to the answer prediction, and improving prediction accuracy. The proposed method was tested on the CommonsenseQA dataset and OpenBookQA dataset, achieving accuracy improvements of 2.08% and 1.23% over the QA-GNN method, respectively. Reference | Related Articles | Metrics | Comments（0）

Select

Mesh Simplification Based on Multi-source Point Cloud Feature Information JIANG Xiao, QIU Chunxia, ZHANG Chunsen, GE Yingwei Journal of Applied Sciences    2025, 43 (2): 301-314.   DOI: 10.3969/j.issn.0255-8297.2025.02.009 Abstract （35）      PDF（pc） （27649KB）（4）       Knowledge map    Save To mitigate the significant loss of important geographic entity structural features in mesh simplification algorithms based on quadratic error functions, this paper presents a mesh simplification method that integrates multi-source point cloud feature information. Firstly, laser point clouds and image dense matching point clouds are fused to enhance the quality of the mesh model. Subsequently, incorporating attributes such as color, elevation and curvature, a region-growing algorithm based on super-voxels is applied to segment the fused point cloud and extract feature information. Finally, the quadratic error matrix is updated using the extracted point cloud feature information to achieve high-precision mesh simplification. Utilizing a three-dimensional mesh constructed from the fused point cloud as experimental data, the proposed algorithm is evaluated and compared with QEM, QEF, and Low-poly algorithms. Experimental results indicate that the proposed method improves simplification accuracy by an average of 39.49%. Reference | Related Articles | Metrics | Comments（0）

Select

Image Digital Copyright Protection System Based on Blockchain LAN Yajie, MA Ziqiang, MIAO Li, HU Fusen Journal of Applied Sciences    2025, 43 (2): 315-333.   DOI: 10.3969/j.issn.0255-8297.2025.02.010 Abstract （59）      PDF（pc） （8139KB）（13）       Knowledge map    Save Traditional copyright management methods rely on centralized servers for storage and verification, which leads to a series of problems, such as difficulty in detecting infringement, complexity in the copyright validation and authorization process, and the absence of an effective similarity retrieval mechanism. These issues make it difficult to provide copyright owners with credible evidence of their copyright. To address these challenges, this paper proposes an image digital copyright protection system based on Hyperledger Fabric blockchain network. The system integrates the scale-invariant feature transform (SIFT) similarity detection algorithm, discrete cosine transform (DCT) zero-watermarking algorithm, chaotic mapping image encryption algorithm, and inter planetary file system (IPFS) for distributed storage. System function tests and performance analyses demonstrate the system’s capability to achieve unique similarity detection, reliable copyright ownership proofs, decentralized encrypted storage, and seamless copyright transfer. These features collectively provide a transparent, safe and open platform for digital image copyright trading, ensuring effective copyright protection for copyright owners. Reference | Related Articles | Metrics | Comments（0）

Select

Joint Extraction of Curriculum Entity Relationships Based on Parallel Decoding and Clustering SUN Lijun, XU Xingjian, MENG Fanjun Journal of Applied Sciences    2025, 43 (2): 334-347.   DOI: 10.3969/j.issn.0255-8297.2025.02.011 Abstract （68）      PDF（pc） （1640KB）（39）       Knowledge map    Save Entity-relation joint extraction, as a core part of knowledge graph construction, aims to extract entity-relation triples from unstructured text. Current joint extraction methods often struggle with decoding inefficiencies, resulting in weak interaction modeling between entities and relations, insufficient context understanding, and redundant information. To address these limitations, we propose a model based on parallel decoding and clustering for entity-relation joint extraction. First, the bidirectional encoder representations from transformers (BERT) model is used for text encoding to obtain character vectors rich in semantic information. Next, a non-autoregressive parallel decoder is employed to enhance interactions between entities and relations. To further optimize decoding results, hierarchical agglomerative clustering is combined with a majority voting mechanism, improving contextual information capture and reducing redundancy. Finally, a high-quality set of triples is generated to construct a curriculum knowledge graph. To evaluate the performance of the proposed method, experiments are conducted on the public datasets NYT and WebNLG, as well as a self-constructed C language dataset. The results show that this method outperforms other models in terms of precision and F1 score. Reference | Related Articles | Metrics | Comments（0）

Select

Leopards Individual Recognition Based on Bi-level Routing Attention and Self-Calibrated Convolution YANG Wan, CHEN Aibin, ZHAO Ying, WU Yue, ZHEN Xin, XIAO Zhishu Journal of Applied Sciences    2025, 43 (2): 348-360.   DOI: 10.3969/j.issn.0255-8297.2025.02.012 Abstract （32）      PDF（pc） （3495KB）（23）       Knowledge map    Save Infrared camera images of leopards in natural environments pose significant challenges for individual recognition due to issues such as high fusion between individuals and their surroundings, as well as high inter-class similarity. To address these challenges, an improved EfficientNet model is proposed, incorporating self-calibrating convolution and bilevel routing attention. The self-calibrating convolution adaptively builds remote space and inter-channel dependencies around each spatial location. The ability to recognize detailed features is enhanced by explicitly combining richer contextual information. This effectively mitigates the recognition challenges posed by high inter-class similarity. Meanwhile, the bilevel routing attention combines the top-down global attention strategy and the bottom-up local attention strategy to solve the problem of high integration between individuals and their environment. Experiment results show that the accuracy of the proposed model reaches 95.56% in the task of leopard individual recognition, which is significantly higher than the original EfficientNet. These findings validate the effectiveness and superiority of the proposed model in dealing with leopard individual recognition task. Reference | Related Articles | Metrics | Comments（0）