To address the issues of high missed detection rates for small objects and interference from complex backgrounds in brain tumor detection, this paper proposes an improved model named YOLO-DCS based on YOLOv8. First, a C2fDAttention module is designed to replace the original backbone network, enhancing feature extraction in tumor regions through a dynamic attention mechanism. Second, the CARAFE (ContentAware ReAssembly of FEatures) upsampling operator is adopted to improve contour reconstruction accuracy for small tumors. Finally, the SEAMHead (Squeeze-and-Excitation Augmented Mask Head) is introduced into the detection head to achieve adaptive fusion of multi-scale features. Experimental results on the dataset demonstrate that the improved model achieves an mAP50 of 97.3 % with only a 0.06 % increase in parameter count, while the recall rate is improved by 3.3 % compared to the original YOLOv8, and the floating-point operations per second are reduced by 8.6 %. This provides a high-precision and lightweight solution for medical image-assisted diagnosis.

Local Interpretable Model-agnostic Explanations (LIME) is an interpretable method used to explain the predictions of machine learning models. It generates perturbed samples around an instance and fits a simple surrogate model, such as linear regression, to approximate the local behavior of the black-box model. This paper introduces Additive Local Interpretable Model (ALIME), a LIME variant based on generalized additive models (GAMs), where feature effects are modeled by penalized splines (P-splines), providing flexibility for capturing nonlinear relationships. Experimental results show that ALIME outperforms the original LIME method in terms of local fidelity. In addition, the shape functions generated by ALIME can clearly capture local feature contributions, providing insight into the relationship between features and model outputs, and enhancing overall interpretability.

Event cameras form a fundamental foundation for visual perception in scenes characterized by high speed and a wide dynamic range. Although deep learning techniques have achieved remarkable success in estimating event-based optical flow, existing methods have not adequately addressed the significance of temporal information in capturing spatiotemporal features. Due to the dynamics of spiking neurons in SNNs, which preserve important information while forgetting redundant information over time, they are expected to outperform analog neural networks (ANNs) with the same architecture and size in sequential regression tasks. In addition, SNNs on neuromorphic hardware achieve advantages of extremely low power consumption. However, present SNN architectures encounter issues related to limited generalization and robustness during training, particularly in noisy scenes. To tackle these problems, this study introduces an innovative spike-based self-supervised learning algorithm known as SeLHIB, which leverages the information bottleneck theory. By utilizing event-based camera inputs, SeLHIB enables robust estimation of optical flow in the presence of noise. To the best of our knowledge, this is the first proposal of a self-supervised information bottleneck learning strategy based on SNNs. Furthermore, we develop spike-based self-supervised algorithms with nonlinear and high-order information bottleneck learning that employs nonlinear and high-order mutual information to enhance the extraction of relevant information and eliminate redundancy. We demonstrate that SeLHIB significantly enhances the generalization ability and robustness of optical flow estimation in various noise conditions. In terms of energy efficiency, SeLHIB achieves 90.44% and 45.70% cut down of energy consumption compared to its counterpart ANN and counterpart SNN models, while attaining 33.78% lower AEE (MVSEC), 5.96% lower RSAT (ECD) and 6.21% lower RSAT (HQF) compared to the counterpart ANN implementations with the same sizes and architectures.

In this article, we propose the concept of flexible linguistic preference relations (FLPRs), in which the flexible linguistic expressions, a more flexible way to form linguistic expressions, are employed. Further, we present a method to rank alternatives based on preference information in FLPRs by exploring the linguistic distribution (LD) and priority-based approximation (PA) of FLPRs. In the LD-based approximation, we first present a two-stage optimization process to approximate FLPRs to distribution linguistic preference relations (DLPRs) following the principles of minimum preference loss and maximum consistency. Then in the PA process, we derive priority vectors from the DLPRs with some desired properties. Finally, a comparative analysis of the priority vectors derived from different kinds of linguistic preference relations is presented to illustrate our proposal.

Various linguistic expressions have been presented to model the flexibility of linguistic preference expressions and to support the consensus reaching in linguistic group decision-making (GDM). In this paper, we propose the concept of flexible linguistic expressions (FLEs) as a general linguistic preference expression format to improve the flexibility of the construction of complex linguistic expressions and the elicitation of linguistic preferences and, then, we develop a new linguistic GDM model with FLEs, referred to as FLE-based GDM (FLEGDM). In the FLEGDM, an FLE aggregation process with accurate constraints is developed to improve the quality (i.e., accuracy) of the collective result as well as guarantee the principle of minimum preference-loss through a mixed 0-1 linear programming model. Meanwhile, the consensus rules with minimum preference-loss are designed to support the consensus reaching process (CRS) in the FLEGDM. Finally, we present the detailed comparative analysis involving different linguistic GDM models to show the advantages of the FLEGDM.

Gene expression is regulated by transcription and translation, and the promoter controls the start of transcription. Finding the exact location of a promoter is of great importance to life science. With the development of the Next-Generation Sequencing (NGS), more and more eukaryotic gene sequence data are available. Computational prediction of eukaryotic promoters has become one of the most challenging problems in sequence analysis. Many methods have been proposed, but the accuracy of prediction still needs to be improved. In this paper we use support vector machine (SVM) to verify that promoter elements are more important than non-elements for predicting promoters. With this factor in mind, we utilize convolution filters to compress non-elements information, and encode elements to emphasize their importance. A new prediction model is constructed based on neural networks. We applied a 10-fold cross validation test to validate the proposed model. We achieved 89.86% accuracy, 86.51% specificity and 89.64% sensitivity, which are better than the other three prediction methods (SVM, NNPP2.2 and CNN).

How can we detect the natural community structure in a social network mingled with anomalous links? The majority of existing methods almost universally ignore these anomalous links (either correct or incorrect), and treat them as ordinary links without taking their particularities into account. From a novel perspective, we focus on handling anomalous links for community detection, since the anomalous links derived from noise directly affect the accuracy of community detection and removing them makes it much easier to comprehend the network topology. Inspired by link prediction, an effective approach is proposed to coarsen networks which removes abnormal links by virtue of the local similarity index. Extensive experiments demonstrate that our strategy achieves higher accuracy than raw networks, especially when a network has high mixing of communities. For real-world networks, the improvement is up to 8.7%. In addition, fine-grained communities, usually revealing rich information in real-world networks, can be well detected.

The linguistic distribution is becoming a popular tool to model linguistic expressions in group decision making. Due to the knowledge limitation, it is difficult for decision makers to provide complete linguistic distribution information and partial ignorance exists in practical group decision making problems. Meanwhile, in group decision making it is hoped to find a group opinion whose distribution information is complete and the preference loss between this group opinion and individual opinions is the minimum. To tackle these issues, this paper introduces the concept of incomplete linguistic distributions and proposes a new model called the minimum preference loss model (MPLM), aiming at minimizing the preference loss between the group opinion and individual opinions in the group decision making with incomplete linguistic distributions. Finally, a numerical example is provided to demonstrate our model.