Search

The least squares twin support vector machine(LSTSVM) is used for emotion recognition. The penalty coefficients，and kernel function parameter of LSTSVM model are difficult to determine, so the modified firefly algorithm(MFA) is used to select the best parameters of the LSTSVM to achieve optimal performance. Based on four modal of physiological signals, which are EEG, skin electrical, electromyography and respiratory signal, the proposed algorithm is used for emotion recognition, and comparisons are made with standard LSTSVM and particle swarm optimization LSTSVM algorithm. Simulation results show that the proposed MFA-LSTSVM algorithm has higher accuracy and shorter training time.

Protein loops play a critical role in the dynamics of proteins and are essential for numerous biological functions, and various computational approaches to loop modeling have been proposed over the past decades. However, a comprehensive understanding of the strengths and weaknesses of each method is lacking. In this work, we constructed two high-quality datasets (i.e. the General dataset and the CASP dataset) and systematically evaluated the accuracy and efficiency of 13 commonly used loop modeling approaches from the perspective of loop lengths, protein classes and residue types. The results indicate that the knowledge-based method FREAD generally outperforms the other tested programs in most cases, but encountered challenges when predicting loops longer than 15 and 30 residues on the CASP and General datasets, respectively. The ab initio method Rosetta NGK demonstrated exceptional modeling accuracy for short loops with four to eight residues and achieved the highest success rate on the CASP dataset. The well-known AlphaFold2 and RoseTTAFold require more resources for better performance, but they exhibit promise for predicting loops longer than 16 and 30 residues in the CASP and General datasets. These observations can provide valuable insights for selecting suitable methods for specific loop modeling tasks and contribute to future advancements in the field. [ABSTRACT FROM AUTHOR]

In order to optimize the design of light-reducing shed of highway tunnels, the height of light-transmitting area on both sides of light-reducing shed is studied. Firstly, numerical analysis is used to study the direct irradiance area and brightness variations of the road surface under different configurations of lighting-reducing shed. By establishing numerical analysis models for lighting-reducing shed with top-diffusing plate and hollow-design on both sides, various optical parameters of lighting-reducing shed and the brightness distribution of road surface are analyzed under different conditions. According to the requirements of direct irradiance area, illuminance of road surface under the shed, and brightness uniformity, a comparative analysis of two conditions is conducted. The light-transmitting area height of light-reducing shed are determined to be three meters for the north side and two meters for the south side, which can mitigate the sudden brightness change when entering and exiting the tunnel, and reduce the glare effect at the tunnel entrance. Driving safety and comfort are enhanced with the improvement of driving environment at the tunnel entrance. [ABSTRACT FROM AUTHOR]

Automated segmentation of abdominal organs and tumors in medical images is a challenging yet essential task in medical image analysis. Deep learning has shown excellent performance in many medical image segmentation tasks, but most prior efforts were fragmented, addressing individual organ and tumor segmentation tasks with specialized networks. To tackle the challenges of abdominal organ and tumor segmentation using partially labeled datasets, we introduce Re-parameterizing Mixture-of-Diverse-Experts (RepMode) to abdominal organ and tumor segmentation. Within the RepMode framework, the Mixture-of-Diverse-Experts (MoDE) block forms the foundation, learning generalized parameters applicable across all tasks. We seamlessly integrate the MoDE block into a U-shaped network with dynamic heads, addressing multi-scale challenges by dynamically combining experts with varying receptive fields for each organ and tumor. Our framework incorporates task encoding in both the encoder–decoder section and the segmentation head, enabling the network to adapt throughout the entire system based on task-related information. We evaluate our approach on the multi-organ and tumor segmentation (MOTS) dataset. Experiments show that DoDRepNet outperforms previous methods, including multi-head networks and single-network approaches, giving a highly competitive performance compared with the original single network with dynamic heads. DoDRepNet offers a promising approach to address the complexities of abdominal organ and tumor segmentation using partially labeled datasets, enhancing segmentation accuracy and robustness. [ABSTRACT FROM AUTHOR]

Background: Multiple observational studies have yielded controversial results regarding the association between Parkinson's disease (PD) and periodontitis. Objective: This systematic review and meta-analysis was conducted to ascertain their bidirectional relationship. Methods: A literature search for relevant studies was performed in PubMed, EMBASE, the Cochrane Library, and Web of Science databases from inception to December 19, 2022. Effect sizes (ES) with 95% confidence intervals were pooled under the random-effects model. Then, leave-one-out sensitivity analysis and contour-enhanced funnel plot were applied to assess the stability of the results. Results: A total of 34 studies and 24 studies were included for systematic review and quantitative meta-analysis, respectively. Pooled ES indicated that periodontitis was not significantly associated with PD risk (HR = 1.13, 95% CI 0.88–1.45, n = 3; OR = 1.94, 95% CI 0.55–6.90, n = 7), while the Mendelian randomization study revealed no association between PD and periodontitis risk (coefficient [B] = –0.0001, standard error = 0.0001, p = 0.19). Furthermore, PD patients exhibited higher levels of periodontal pocket depth (SMD = 1.10, 95% CI 0.53–1.67), clinical attachment level (SMD = 1.40, 95% CI 0.55–2.26), plaque index (SMD = 0.81, 95% CI 0.22–1.39), and Oral Health Impact Profile-14 score (SMD = 0.91, 95% CI 0.33–1.49) compared to healthy controls. Conclusions: Our meta-analysis identified no bidirectional association between PD risk and periodontitis risk, though the prevalence of periodontitis and poorer oral status was higher in PD patients. [ABSTRACT FROM AUTHOR]