Explore the vast range of titles available.

With the introduction of concepts such as ubiquitous mapping, mapping-related technologies are gradually applied in autonomous driving and target recognition. There are many problems in vision measurement and remote sensing, such as difficulty in automatic vehicle discrimination, high missing rates under multiple vehicle targets, and sensitivity to the external environment. This paper proposes an improved RES-YOLO detection algorithm to solve these problems and applies it to the automatic detection of vehicle targets. Specifically, this paper improves the detection effect of the traditional YOLO algorithm by selecting optimized feature networks and constructing adaptive loss functions. The BDD100K data set was used for training and verification. Additionally, the optimized YOLO deep learning vehicle detection model is obtained and compared with recent advanced target recognition algorithms. Experimental results show that the proposed algorithm can automatically identify multiple vehicle targets effectively and can significantly reduce missing and false rates, with the local optimal accuracy of up to 95% and the average accuracy above 86% under large data volume detection. The average accuracy of our algorithm is higher than all five other algorithms including the latest SSD and Faster-RCNN. In average accuracy, the RES-YOLO algorithm for small data volume and large data volume is 1.0% and 1.7% higher than the original YOLO. In addition, the training time is shortened by 7.3% compared with the original algorithm. The network is then tested with five types of local measured vehicle data sets and shows satisfactory recognition accuracy under different interference backgrounds. In short, the method in this paper can complete the task of vehicle target detection under different environmental interferences.

Accurate segmentation in medical imaging requires loss functions that capture both regional overlap and boundary alignment. This study evaluates composite losses combining binary cross-entropy (BCE) and a boundary-based term under fixed and adaptive weighting schemes, using U-Net and SwinUNETR on the MM-WHS dataset. For U-Net, a small boundary contribution with adaptive weighting yielded the best results: Standard SoftAdapt (90/10 BCE + BoundaryDoU) achieved the highest Dice score ( ), surpassing both the baseline ( ) and fixed ratios. In contrast, SwinUNETR achieved its strongest performance with a fixed 70% BCE + 10% boundary ratio (0.919 ± 0.02). The result showed that combining a boundary-based loss term helps improve the segmentation accuracy. However, the performance gain is dependent on the architecture of the segmentation model; convolution-based U-Net benefited from the adaptive loss weighting scheme, whereas Transformer-based SwinUNETR without strong inductive bias did not benefit from increased influence of the boundary loss term.

Background Accurately identifying RNA 2ʹ-O-methylation (2OM) sites is a crucial step in gaining an in-depth understanding of RNA regulatory mechanisms. Although there are currently multiple prediction tools available, they still suffer from limited prediction accuracy and an inability to fully capture the associations between sequences and sites. Results This study constructs a novel low-redundancy dataset and innovatively proposes the KN-PairMatrix encoding scheme, effectively addressing the research gap in sequence-site association analysis. Based on this foundation, we developed the deep learning framework OMetaNet, which integrates residual and downsampling-optimized CNN modules, Mamba network, and a proprietary cross-modal interactive fusion module. The framework incorporates a contrastive learning-driven adaptive hybrid loss function. Employing a progressive feature disentanglement strategy, it enhances the learning capability for 2OM site-specific patterns. Independent evaluation results demonstrate that OMetaNet significantly outperforms existing methods in predicting 2OM sites across all four nucleotide types. Conclusions We proposed a novel computational model, OMetaNet. Its unique design structure may potentially reshape the paradigm of transcriptome analysis, open up new directions for extracting modification site information, and show significant potential in biomarker research and cross-species generalization studies.

Hate speech detection is a challenging task due to complexities such as language ambiguity, limited context, cultural nuances, and situational factors. This challenge is further amplified in low-resource languages, i.e. Urdu. Most research on hate speech detection has focused primarily on resource rich language i.e. English, leaving Urdu significantly understudied. This paper presents a novel approach to enhance Urdu hate speech detection by leveraging differential transfer learning combined with adaptive loss functions. We utilize pre-trained models from resource-rich languages to capture semantic features relevant to hate speech and implement a differential transfer mechanism to adapt these models to the unique linguistic, and cultural characteristics of Urdu. We addressed cultural and linguistic differences by including specific datasets designed to suit certain cultures, using multilingual embeddings, and applying contextualization approaches that take into account the cultural specifics of language use. We created a Nastaliq Urdu dataset consisting of hate, offensive, and neutral labels for YouTube comments, totaling 18,058 records. To address class imbalance in the dataset, we propose an adaptive loss function that assigns higher penalties to misclassifications of hate speech, thereby improving model sensitivity toward this minority class. Our research employs a range of machine learning algorithms, including random forests, support vector machines, decision trees, recurrent neural networks, long short-term memory networks, and transfer learning methods. The results indicate that transfer learning outperforms conventional machine learning and deep learning techniques, improving F1 scores from 81% to above 89%. Notably, our proposed DAmBERT model achieved a weighted F1 score of 91.49% by incorporating pre-trained embeddings, outperforming all other classifiers. These findings highlight the potential of combining differential transfer learning and customized loss functions to develop robust hate speech detection systems for Urdu.

Accurate wind power prediction can increase the utilization rate of wind power generation and maintain the stability of the power system. At present, a large number of wind power prediction studies are based on the mean square error (MSE) loss function, which generates many errors when predicting original data with random fluctuation and non-stationarity. Therefore, a hybrid model for wind power prediction named IVMD-FE-Ad-Informer, which is based on Informer with an adaptive loss function and combines improved variational mode decomposition (IVMD) and fuzzy entropy (FE), is proposed. Firstly, the original data are decomposed into K subsequences by IVMD, which possess distinct frequency domain characteristics. Secondly, the sub-series are reconstructed into new elements using FE. Then, the adaptive and robust Ad-Informer model predicts new elements and the predicted values of each element are superimposed to obtain the final results of wind power. Finally, the model is analyzed and evaluated on two real datasets collected from wind farms in China and Spain. The results demonstrate that the proposed model is superior to other models in the performance and accuracy on different datasets, and this model can effectively meet the demand for actual wind power prediction.

Video action segmentation is a crucial task in evaluating the ability to understand human activities. Previous works on this task mainly focus on capturing complex temporal structures and fail to consider the feature ambiguity among similar actions and the biased training sets, thus they are easy to confuse some actions. In this paper, we propose a novel action segmentation framework, called DeConfuNet, to solve the above issue. First, we design a discriminative enhancement module (DEM) trained by an adaptive margin-guided discriminative feature learning which adjusts the margin adaptively to increase the feature distinguishability among similar actions, and whose multi-stage reasoning and adaptive feature fusion structures provide structural advantages for distinguishing similar actions. Second, we propose an equalizing influence module (EIM) that can overcome the impact of biased training sets by balancing the influence of training samples under a coefficient-adaptive loss function. Third, an energy and context-driven refinement module (ECRM) further alleviates the impact of the unbalanced influence of training samples by fusing and refining the inference of DEM and EIM, which utilizes the phased prediction including context and energy clues to assimilate untrustworthy segments, alleviating over-segmentation hugely. Extensive experiments show the effectiveness of each proposed technique, they verify that the DEM and EIM are complementary in reasoning and cooperate to overcome the confusion issue, and our approach achieves significant improvement and state-of-the-art performance of accuracy, edit score, and F1 score on the challenging 50Salads, GTEA, and Breakfast benchmarks.

The extreme learning machine (ELM) algorithm is advantageous to regression modeling owing to its simple structure, fast computation, and good generalization performance. However, the existing ELM algorithm uses an l 2 -norm loss function, which is sensitive to outliers and has low robustness. In addition, some existing robust loss functions are not sufficiently flexible to accurately estimate the relationship between sample points and loss values, resulting in unsatisfactory ELM performance. To address these problems, this study established a robust ELM (ALFELM) algorithm. First, an adaptive loss function with two tunable hyperparameters was introduced; the function can be transformed into several robust loss functions by varying the parameters. It overcomes the limitations of fixed robust loss functions. Then, the Bayesian optimization strategy was used to determine the optimal parameters of the loss function. Furthermore, the classical iterative reweighted least squares method was used to solve for output weights, with a weight function corresponding to the loss function and a regularization parameter to prevent overfitting. Finally, the proposed method was tested using several artificial and benchmark datasets, and its effectiveness was verified for a real engineering case. The results indicated that the proposed ALFELM algorithm is more robust and accurate compared with other methods, especially for a large number of outliers. In addition, the algorithm can be used to establish effective regression models for actual processes.

Fuzzy cognitive maps (FCMs) learning is a hot topic in recent years. However, as the number of concepts increases in FCMs, it is difficult to learn the sparse and robust FCMs from a small amount of data, especially from noise data. In this paper, a new large-scale FCMs learning method based on the sparse regression of adaptive loss function is presented, marked as AQP-FCM. Adaptive loss function and L1-norm are introduced in the model to deal with noise data. We solve the model by ADMM method and quadratic programming method to learn the FCMs better. Moreover, the convergence of model is proved. We did a series of experiments under the synthetic data of time series and noise synthesis data. AQP-FCM is also applied to reconstruct gene regulatory network (GRNs). The results of the experiments show that the proposed AQP-FCM method has good performance.

Designing appropriate loss functions is critical to the success of supervised learning models. However, most conventional losses are fixed and manually designed, making them suboptimal for diverse and dynamic learning scenarios. In this work, we propose an Adaptive Meta-Loss Network (Adaptive-MLN) that learns to generate task-agnostic loss functions tailored to evolving classification problems. Unlike traditional methods that rely on static objectives, Adaptive-MLN treats the loss function itself as a trainable component, parameterized by a shallow neural network. To enable flexible, gradient-free optimization, we introduce a hybrid evolutionary approach that combines Genetic Algorithms (GA) for global exploration and Evolution Strategies (ES) for local refinement. This co-evolutionary process dynamically adjusts the loss landscape, improving model generalization without relying on analytic gradients or handcrafted heuristics. Experimental evaluations on synthetic tasks and the CIFAR-10 and MNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy, convergence, and adaptability.

The rapid spread of fires underscores the urgency of high-accuracy fire smoke detection for public safety, but early fires pose major challenges—small flame/smoke targets, blurred boundaries, low contrast, and complex background interference—limiting the performance of existing models. To address these issues, this paper proposes SFFA-YOLO, an engineering-oriented improved algorithm based on the YOLOv11 framework for fire smoke detection, which achieves a balanced trade-off between detection precision, real-time performance, and lightweight deployment. The model integrates three synergistic optimization modules for targeted scene adaptation: (1) the FMFA module for cross-scale feature fusion to enhance thin smoke and small flame recognition; (2) the SGCA module for joint channel-spatial feature focusing to improve target localization accuracy; (3) the SDA-Loss function for dynamic weight adjustment based on target size and clarity to stabilize small target detection. Validated on the self-built FS-Blend dataset (supplemented with difficult samples such as distant thin smoke and backlit flames), SFFA-YOLO outperforms mainstream models (YOLOv8, YOLOv9, Faster R-CNN) in key metrics. Compared with the YOLOv11s baseline, it achieves a 2.5% Precision improvement and 3.9% mAP@0.5 improvement while reducing parameters by 12.8%, confirming its reliability as a real-time fire smoke detection solution.