Haiyang Zhang

Agricultural diseased leaf image segmentation is a critical technology for precision agriculture and intelligent crop protection. To overcome the limitations of current segmentation methods-such as imprecise leaf edge extraction, difficulty in detecting small disease lesions, and insufficient robustness in complex backgrounds-this paper proposes an agricultural diseased leaf image segmentation method based on an enhanced visual state space model, named MSVM-UNet (Multi-Scale Spatial Attention Vision Mamba U-Net). This method employs an encoder-decoder framework and integrates improved Visual State Space (VSS) modules in both the encoder and decoder, enhancing long-range dependency modeling and local-global feature fusion. Simultaneously, a Multi-Scale Spatial Attention (MSSA) module is introduced in the skip connections to enhance cross-scale feature representation and capture fine boundary details of disease spots. To simulate real field imaging conditions, we perform random horizontal or vertical flips on the images and randomly adjust hue, saturation, and brightness before training. Experimental results demonstrate that, compared with mainstream methods, MSVM-UNet achieves significant performance improvement in agricultural diseased leaf segmentation tasks, reaching 80.44% mIoU and 92.56% Dice on the validation set, providing our solution for intelligent agricultural disease monitoring.

The rapid growth of biomedical publications has presented significant challenges in the field of information retrieval. Most existing work focuses on document retrieval given explicit queries. However, in real applications such as curated biomedical database maintenance, explicit queries are missing. In this paper, we propose a two-step model for biomedical information retrieval in the case that only a small set of example documents is available without explicit queries. Initially, we extract keywords from the observed documents using large pre-trained language models and biomedical knowledge graphs. These keywords are then enriched with domain-specific entities. Information retrieval techniques can subsequently use the collected entities to rank the documents. Following this, we introduce an iterative Positive-Unlabeled learning method to classify all unlabeled documents. Experiments conducted on the PubMed dataset demonstrate that the proposed technique outperforms the state-of-the-art positive-unlabeled learning methods. The results underscore the effectiveness of integrating large language models and biomedical knowledge graphs in improving zero-shot information retrieval performance in the biomedical domain.

Cross-domain recommendation aims to leverage heterogeneous information to transfers knowledge from a data-sufficient domain (source domain) to a data-scarce domain (target domain). Existing approaches mainly focus on learning single-domain user preferences and then employ a transferring module to obtain cross-domain user preferences, but ignore the modeling of users' domain specific preferences on items. We argue that incorporating domain-specific preferences from the source domain will introduce irrelevant information that fails to the target domain. Additionally, directly combining domain-shared and domain-specific information may hinder the target domain's performance. To this end, we propose C^2DR, a novel approach that disentangles domain-shared and domain-specific preferences from a causal perspective. Specifically, we formulate a causal graph to capture the critical causal relationships based on the underlying recommendation process, explicitly identifying domain-shared and domain-specific information as causal irrelevant variables. Then, we introduce disentanglement regularization terms to learn distinct representations of the causal variables that obey the independence constraints in the causal graph. Remarkably, our proposed method enables effective intervention and transfer of domain-shared information, thereby improving the robustness of the recommendation model. We evaluate the efficacy of C^2DR through extensive experiments on three real-world datasets, demonstrating significant improvements over state-of-the-art baselines.

Rapid and precise detection and classification of vehicles are vital for the intelligent transportation systems (ITSs). However, due to small gaps between vehicles on the road and interference features of photos, or video frames containing vehicle images, it is difficult to detect and identify vehicle types quickly and precisely. For solving this problem, a new vehicle detection and classification model, named YOLOv4_AF, is proposed in this paper, based on an optimization of the YOLOv4 model. In the proposed model, an attention mechanism is utilized to suppress the interference features of images through both channel dimension and spatial dimension. In addition, a modification of the Feature Pyramid Network (FPN) part of the Path Aggregation Network (PAN), utilized by YOLOv4, is applied in order to enhance further the effective features through down-sampling. This way, the objects can be steadily positioned in the 3D space and the object detection and classification performance of the model can be improved. The results, obtained through experiments conducted on two public data sets, demonstrate that the proposed YOLOv4_AF model outperforms, in this regard, both the original YOLOv4 model and two other state-of-the-art models, Faster R-CNN and EfficientDet, in terms of the mean average precision ( mAP ) and F1 score , by achieving respective values of 83.45% and 0.816 on the BIT-Vehicle data set, and 77.08% and 0.808 on the UA-DETRAC data set.

The automatic generation of a text summary is a task of generating a short summary for a relatively long text document by capturing its key information. In the past, supervised statistical machine learning was widely used for the Automatic Text Summarization (ATS) task, but due to its high dependence on the quality of text features, the generated summaries lack accuracy and coherence, while the computational power involved, and performance achieved, could not easily meet the current needs. This paper proposes four novel ATS models with a Sequence-to-Sequence (Seq2Seq) structure, utilizing an attention-based bidirectional Long Short-Term Memory (LSTM), with added enhancements for increasing the correlation between the generated text summary and the source text, and solving the problem of out-of-vocabulary (OOV) words, suppressing the repeated words, and preventing the spread of cumulative errors in generated text summaries. Experiments conducted on two public datasets confirmed that the proposed ATS models achieve indeed better performance than the baselines and some of the state-of-the-art models considered.

This paper proposes an RG hyperparameter optimization approach, based on a sequential use of random search (R) and grid search (G), for improving the blood glucose level prediction of boosting ensemble learning models. An indirect prediction of blood glucose levels in patients is performed, based on historical medical data collected by means of physical examination methods, using 40 human body’s health indicators. The conducted experiments with real clinical data proved that the proposed RG double optimization approach helps improve the prediction performance of four state-of-the-art boosting ensemble learning models enriched by it, achieving 1.47% to 24.40% MSE improvement and 0.75% to 11.54% RMSE improvement.

The accuracy of behavioral interactive features is a key factor for improving the performance of rating prediction. In order to deeply explore the potential rules of user behavior and enhance the accurate representation of interactive features, this paper proposes two rating prediction models, based on the spatial dimension and distance measurement (SDDM), under the premise of taking the mean value of the user behavior history as a user feature, and obtaining the interactive features of an item and a user by calculating the distance between them in each feature dimension. In the proposed SDDM-Var and SDDM-PCC models, the variance and the Pearson correlation coefficient (PCC) are respectively utilized to evaluate the user’s attention to each feature dimension as to further obtain the weight vector of the interactive features. Finally, in order to improve the generalization ability of the proposed models, the rating prediction is accomplished by means of a specially designed multi-layer full-connection neural network. The conducted experiments with two public MovieLens datasets demonstrate the superior rating prediction performance of the proposed models in comparison with the existing baseline models, in terms of the root mean square error (RMSE), by achieving values of 0.865 and 0.872 on MovieLens 100K, and 0.839 and 0.832 on MovieLens 1M, respectively for SDDM-Var and SDDM-PCC.

Matrix Factorization (MF) is one of the most successful Collaborative Filtering (CF) techniques used in recommender systems due to its effectiveness and ability to deal with very large user-item rating matrix. However, when the rating matrix sparseness increases its performance deteriorates. Expanding MF to include side-information of users and items has been shown by many researchers both to improve general recommendation performance and to help alleviate the data-sparsity and cold-start issues in CF. In regard to item feature side-information, most schemes incorporate this information through a two stage process: intermediate results (e.g., on item similarity) are first computed based on item attributes; these are then combined with MF. In this paper, focussing on item side-information, we propose a model that directly incorporates item features into the MF framework in a single step process. The model, which we name FeatureMF, does this by projecting every available attribute datum in each of the item features into the same latent factor space with users and items, thereby in effect enriching item representation in MF. Results are presented of comparative performance experiments of the model against three state-of-the-art item information enriched models, as well as against four reference benchmark models, using two public real-world datasets, Douban and Yelp, with four training:test ratio scenarios each. It is shown to yield the best recommendation performance over all these models across all contexts including data-sparsity situations, in particular, achieving over 0.9% to over 6.5% MAE recommendation performance improvement over the next best model, HERec. FeatureMF is also found to alleviate cold start and to scale well, almost linearly, in regard to computational time, as a function of dataset size.