A Feature Fusion-Based Service Classification Approach for Collaborative Development

With the rapid development of information technology and the Internet, text information on various media platforms, such as blogs, microblogs, and news, has exploded. In order to process these text data more efficiently, text classification technology has gradually become a research focus. In view of the common problems of incomplete structure and sparse features in short texts, this paper designs a short text classification model with multi-level semantic feature fusion to effectively extract key word features and sentence features from short texts. The model first uses BERT for preliminary semantic feature extraction, and then combines the first-layer Bi-GRU and the word-level self-attention mechanism to enhance the weight of important semantic information in the text. Next, the second-layer Bi-GRU and the sentence-level self-attention mechanism are used to achieve feature fusion at the word vector and sentence vector levels. The maximum pooling strategy of CNN is used to screen the best features and predict the category probability. In addition, the loss function is adjusted, a threshold is introduced to screen and continuously train samples that are difficult to classify, and an adaptive adjustment factor is added in the back propagation to adaptively attenuate the learning rate and accelerate the model fitting process. In the experiment of 20 Newsgroups dataset, compared with the baseline model, the classification accuracy of this model increased by 3.51% to 88.74%, which effectively proved the effectiveness of this model in improving the classification accuracy of Chinese short texts.

In order to further mine the deep semantic information of the microbial text of public health emergencies, this paper proposes a multichannel microbial sentiment analysis model MCMF-A. Firstly, we use word2vec and fastText to generate word vectors in the feature vector embedding layer and fuse them with lexical and location feature vectors; secondly, we build a multichannel layer based on CNN and BiLSTM to extract local and global features of the microbial text; then we build an attention mechanism layer to extract the important semantic features of the microbial text; thirdly, we merge the multichannel output in the fusion layer and use soft; finally, the results are merged in the fusion layer, and a surtax function is used in the output layer for sentiment classification. The results show that the F1 value of the MCMF-A sentiment analysis model reaches 90.21%, which is 9.71% and 9.14% higher than the benchmark CNN and BiLSTM models, respectively. The constructed dataset is small in size, and the multimodal information such as images and speech has not been considered.

Towards using visual, semantic and structural features to improve code readability classification

A new medical image retrieval approach based on low-level features and high-level semantic features is proposed. The image is segmented into several sub-images by fuzzy C-mean clustering algorithm. After extracting the three gray features, in order to emphasize shape and texture features, the sub-image is changed to binary image, and seven shape features and four texture features are extracted. To decrease feature vector dimension, genetic algorithm is used. The optimizing features constitute the visual contents. Only using these low-level features can't get satisfying results, because these features can't entirely describe human recognition to images, the semantic features are needed, but it is difficult to extract the image semantic contents directly at the present time, so the text information in the image report by radiologists is chosen for semantic content. Experimental results show that the retrieval integrating low-level visual features and text information is better than that only by visual contents.

Remote sensing image scene classification faces challenges, such as the difference in semantic granularity of different scene categories and the imbalance of the number of samples, which cause the wrong features learning for deep convolutional networks (DCNs). This article proposes a multiple granularity semantic learning network (MGSN), including multiple granularity semantic learning (MGSL) and nonuniform sampling augmentation (NUA) modules. Specifically, the MGSL module makes full use of different granularities of semantic information of scenes, guiding the network to learn global and local features simultaneously. And, the relationship between semantic features of different granularity has been explored, based on which the learning of coarse-grained features helps to improve the learning of fine-grained semantic features. It shows that learning fine-grain semantics can inhibit learning coarse-grain semantic features. The NUA module combines sampling and sample augmentation to balance the sample distribution, which can avoid overfitting caused by oversampling. The proposed MGSN achieved state-of-the-art classification accuracy on two large-scale remote sensing image scene classification datasets, Million-AID and NWPU-RESISC45. Under 10<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 20<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> training samples of the NWPU-RESISC45 dataset, MGSN achieves 91.92<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 94.33<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> top-1 accuracy, respectively. In experiments conducted on the Million-AID dataset, the proposed MGSN performed best among 18 DCNs. In comparison to the baseline, FixEfficientNet, MGSN improved the accuracy of top-1 and top-5 by 10.63<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> and 5.47<inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula>, respectively, with low complexity costs.

A multi-scale semantic feature fusion method for remote sensing crop classification

The exploding number of computational models produced by Systems Biologists over the last years is an invitation to structure and exploit this new wealth of information. Researchers would like to trace models relevant to specific scientific questions, to explore their biological content, to align and combine them, and to match them with experimental data. To automate these processes, it is essential to consider semantic annotations, which describe their biological meaning. As a prerequisite for a wide range of computational methods, we propose general and flexible similarity measures for Systems Biology models computed from semantic annotations. By using these measures and a large extensible ontology, we implement a platform that can retrieve, cluster, and align Systems Biology models and experimental data sets. At present, its major application is the search for relevant models in the BioModels Database, starting from initial models, data sets, or lists of biological concepts. Beyond similarity searches, the representation of models by semantic feature vectors may pave the way for visualisation, exploration, and statistical analysis of large collections of models and corresponding data.

The flood prevention case text matching method can assist substations in quickly obtaining reference cases and formulating effective flood prevention strategies. However, the non-standard syntax structure and semantic differences in the context make it extremely difficult to consider contextual information fully. Additionally, existing methods struggle to capture character-level similarity features and the non-linear relationships between features. To enhance the discriminative ability of text matching, this paper proposes an improved text matching model based on ALBERT for substation flood prevention cases. Firstly, a semantic feature enhancement strategy based on BiLSTM is adapted to capture long-term dependencies and contextual information between two texts further. Then, this paper proposes a semantic-character cross-feature fusion strategy to integrate text semantic feature vectors and character-level similarity feature vectors, allowing the model to understand the information in the sequence more comprehensively. Finally, a text interaction feature extraction strategy based on LightGBM is developed to replace ALBERT’s original output layer, which can accurately capture the nonlinear relationship between the two text sentences. The experimental results show that the proposed text matching method outperforms mainstream text matching models in terms of precision, recall, and F1 score. The improved text matching strategy can effectively enhance the accuracy of substation flood prevention text matching and provide strong support for substation flood prevention.

Urbanization has been a driving force for economic growth, yet it has also caused the emergence of informal urban settlements such as urban villages (UVs), which are characterized by issues such as arbitrary land use, high-density construction, and insufficient infrastructure. In previous studies on UV detection, the semantic imbalance and feature interaction among cross-modal data have not been comprehensively considered, impacting the accuracy and interpretability of the results. In this work, a cross-modal fusion framework is proposed that integrates high-resolution remote sensing and street view images for UV detection. First, convolutional neural networks (ResNet-50) are used for feature extraction from both remote sensing and street view images. Then, an inner product channel attention module is used to dynamically adjust weights while considering multiangle views of street view images. A cross-modal feature fusion module that incorporates dilation convolution and a global-based feature fusion block is used to enhance feature interaction and fusion. The method has an overall accuracy (OA) of 0.975 for UV classification in a case study of the Guangzhou–Foshan metropolitan area in China, outperforming a set of baseline methods. The integration of remote sensing and street view images improves the OA value by approximately 2%. This work enhances the understanding of the distribution of UVs via both top-down and ground-level view data in an automatic and efficient way, providing urban planners with valuable insights to accurately identify UVs and support targeted, sustainable urban renewal aligned with the SDGs for inclusive, resilient cities.

Heterogeneous data have become a key issue restricting the monitoring accuracy of volcanic ash cloud and rapid application of remote sensing. In view of the characteristics of classification and heterogeneous data in volcanic ash cloud monitoring, a monitoring method of volcanic ash cloud using feature fusion, convolutional neural networks (CNN) and long short-term memory (LSTM) (FF–CNN–LSTM) is presented in this paper. In this method, firstly, the target features in image are identified by CNN and the time sequence information in text is extracted by LSTM. Secondly, the mapping relationship between text information and image features is learned by fusing image target and text high-level features, and then the identification and diffusion of volcanic ash cloud from heterogeneous data containing only image and text were performed. Finally, the presented FF–CNN–LSTM method is tested by the simulation experiment and the true heterogeneous data of Enta volcanic ash cloud case. The experimental results show that compared with the single CNN, LSTM and the simple combination between CNN and LSTM (CNN–LSTM), the presented FF–CNN–LSTM method in this paper can be fitted with less training steps and has high accuracy and low loss rate; the obtained distribution of volcanic ash cloud is clear and intuitive and has the characteristics with fewer model parameters, simple calculation and high accuracy. It also shows the feasibility and effectiveness of the presented method in volcanic ash cloud monitoring to some extent. The results reveal that the presented method can potentially contribute the monitoring of volcanic ash cloud and disaster prevention and mitigation.

Software quality attributes, such as reliability, security, and usability, are often well-defined and understood at the requirement level. They lay the ground foundation necessary to achieve high-quality, robust, user-friendly, and trustworthy software systems. However, when addressing these attributes at the code level, two significant challenges emerge. First, they tend to scatter across the codebase due to improper encapsulation of object-oriented classes, hampering the visibility of quality-related components across the codebase. Second, they become tangled within a single module due to intricate interdependencies with functional aspects of the code. Addressing quality concerns in the presence of scattered and tangled code can lead to unforeseen issues. For example, software developers may inadvertently introduce new and latent bugs or incorrectly implement code components deviating from the original system-wide requirements. To tackle these pressing issues, this dissertation proposes a series of state-of-the-art solutions integrating ML-based techniques and NLP-based techniques, including static program analysis techniques, to automatically and effectively detect and repair quality concerns present at the code level, even when scattered across the codebase. Additionally, we introduce program structural analysis and change impact analysis, complemented by other unsupervised ML-based techniques, to disentangle quality-related changes from functional ones, to gain a holistic understanding of a particular maintenance task. From a practical stance, our techniques can be integrated for quality risk assessment purposes and incorporated into safety-critical continuous integration systems to monitor the evolving nature of quality concerns. Furthermore, they can enhance bidirectional traceability across evolving software artifacts, such as bug reports, commit messages, and source code, and facilitate bug triaging systems for prioritizing the resolution of highly impacted quality-related bugs.

Image inpainting has achieved great advances by simultaneously leveraging image structure and texture features. However, due to lack of effective multi-feature fusion techniques, existing image inpainting methods still show limited improvement. In this paper, we design a deep multi-feature co-learning network for image inpainting, which includes Soft-gating Dual Feature Fusion (SDFF) and Bilateral Propagation Feature Aggregation (BPFA) modules. To be specific, we first use two branches to learn structure features and texture features separately. Then the proposed SDFF module integrates structure features into texture features, and meanwhile uses texture features as an auxiliary in generating structure features. Such a co-learning strategy makes the structure and texture features more consistent. Next, the proposed BPFA module enhances the connection from local feature to overall consistency by co-learning contextual attention, channel-wise information and feature space, which can further refine the generated structures and textures. Finally, extensive experiments are performed on benchmark datasets, including CelebA, Places2, and Paris StreetView. Experimental results demonstrate the superiority of the proposed method over the state-of-the-art. The source codes are available at https://github.com/GZHU-DVL/MFCL-Inpainting.

Apple leaf diseases (ALD) pose a significant challenge to global apple production, and accurately identifying ALD is crucial for reducing pesticide use and improving fruit quality, particularly in the context of smart agriculture. However, traditional approaches rely on single-model feature extraction, failing to account for relationships between different tasks, which limits their applicability in the apple industry. To address this, we design an optimized convolutional neural network–vision transformer (CNN–ViT) hybrid framework named ResViT-AM, focusing on domain-specific enhancement rather than architectural novelty. Instead of proposing a completely new structure, this work refines existing CNN–Transformer paradigms through task-oriented feature fusion and adaptive attention weighting, tailored for apple leaf disease classification under complex orchard conditions. Using a weighted attention fusion mechanism, our model dynamically integrates features extracted by Residual Network 101 (ResNet-101) and vision transformer (ViT), combining proven architectures in a task-adaptive way rather than pursuing architectural innovation, blending the local convolutional details of Residual Network (ResNet) with the global contextual features of ViT. This approach enhances the model’s representation capability and allows parallel processing of multiple tasks, thereby saving training time and computational resources. Additionally, we evaluate on the public AppleLeaf dataset, which reflects real-world outdoor conditions. On its held-out test split, our model achieves 99.14% top-1 accuracy on the AppleLeaf test split, indicating promising performance under complex orchard conditions. Compared with representative convolutional baselines, ResViT-AM shows greater stability and adaptability on challenging cases, offering a competitive and practical solution for automated apple leaf disease diagnosis.

With the continuous increase in the economic value of new digital currencies represented by Bitcoin, more and more cybercriminals use malicious code to occupy victims system resources and network resources for mining without the victims permission, thereby obtaining cryptocurrency. This type of malicious code named malicious mining code has brought considerable influence and harm to society, enterprises and users. The mining code always conceals the fact that it consumes computer resources in a way that is difficult for ordinary people to discover. This paper proposes a malicious mining code detection method based on feature fusion and machine learning. First, we analyze from static analysis methods and statistical analysis methods to extract multi-dimensional features. Then for multi-dimensional text features, feature vectors are extracted through the n-gram model and TF-IDF, and best feature vectors are selected through the classifier and we fuse these best feature vectors with other statistic features to train our detection model. Finally, automatic detection is performed based on the machine learning framework. The experimental results show that the recognition accuracy of our method can reach 98.0%, its f1 score reach 0.969, and the ROCs AUC reach 0.973.

Single image deraining is an important preprocessing task, as rain streaks awfully reduce the image quality and hinder the subsequence outdoor multimedia issues. In this paper, we explore the multi-resolution representation for rain streaks through parallel hierarchical structure and multi-scale feature extraction and fusion, termed Multi-resolution Parallel Aggregation Network (MPA-Net) in end-to-end manner. Specially, considering the significant role of multi-resolution, we employ the first stage to capture the high-resolution features, progressively introduce high-to-low resolution streams to produce more stages, and then connect all stages in parallel. In each stage, Densely Connected Residual (DCR) block is involved to guide the feature extraction. Besides, Cross-Scale Feature Fusion (CSFF) is first introduced to receive and consolidate the correlated features from different scales followed with Squeeze-and-Excitation (SE) blocks, leading to rich the resolution representations. Extensive experiments demonstrate that our method outperforms the recent comparing approaches on the frequent-use synthetic and real-world datasets.KeywordsSingle image derainingMulti-resolution parallelCross-Scale Feature Fusion