Search

In the field of machine learning, multilabel learning gradually evolved from the traditional text classification problem. In this study, a multiview multilabel via optimal classifier chain (MVMLOCC) algorithm based on the nearest-neighbor model is proposed. The algorithm model establishes a multilabel chain classifier for each view of the dataset and predicts unknown data samples by dynamically adjusting the weights of chain learners. When an unknown example is input, multiple chain classifier models are multiplied by corresponding weights to obtain the final tag set situation. The model makes full use of the relevance between multiple tags and the complementarity and integrity between multiple perspectives and can achieve better learning results. The final experimental results show that our proposed model can be applied to different multilabel classification tasks and has achieved excellent performance under different evaluation indicators. This study mainly studies the multiview and multilabel classification method and uses active learning technology to solve the problem of high label components in data collection. [ABSTRACT FROM AUTHOR]

Infrared image target recognition provides an important means of night traffic management and battlefield environment monitoring. With the improvement of the performance of infrared sensors and the popularization of applications, it becomes possible to obtain multiview infrared images of the same target in the same scene. A target recognition method combining multiview infrared images is proposed. At first, the internal correlation analysis of multiview infrared images is performed based on the nonlinear correlation information entropy (NCIE). The view subset from all the multiview images with the largest NCIE is selected as candidate samples for the subsequent target recognition. The joint sparse representation (JSR) is used to classify all infrared images in the candidate view subset. JSR can effectively investigate the internal correlation of multiple related sparse representation problems and improve the reconstruction accuracy and classification capabilities. In the experiments, the tests are performed on the collected infrared images of multiple types of traffic vehicles, under the conditions of original, noisy, and occluded samples. The effectiveness and robustness of the proposed method can be verified by comparative analysis. [ABSTRACT FROM AUTHOR]

Background. Intralymphatic immunotherapy (ILIT) is short-course administration of allergen-specific immunotherapy (AIT). This study is aimed at assessing the clinical efficacy and safety of ILIT in patients with allergic rhinitis (AR). Methods. MEDLINE, PUBMED, and Cochrane Library were used to conduct electronic searches for clinical trials comparing ILIT and placebo in patients with AR. The final search took place on August 24, 2022. Cochrane Handbook for Systematic Reviews of Interventions was used to assess the risk of bias in the included studies. The outcomes included combined symptom and medication scores (CSMS), visual analog scale (VAS), allergic rhinoconjunctivitis quality of life (RQLQ), Skin-prick test (SPT), and adverse events (AEs). Data were synthesized as mean difference (MD)/standard mean difference (SMD) or risk difference (RD) and 95% confidence interval (CI). Results. Thirteen studies (454 participants) were included in this study. The ILIT group had better clinical improvement on the CSMS (random effects model, SMD-0.85, 95% CI [-1.58, -0.11], P = 0.02) and RQLQ (fixed-effects model, MD-0.42, 95% CI [0.69, 0.15], P = 0.003) than the placebo group. The booster injection was beneficial for CSMS (P < 0.0001), and the 4-week injection interval was superior to the 2-week injection period for improving VAS (P < 0.0001). Local swelling or erythema was the main AE following injection (random effects model, RD 0.16, 95% CI [0.05, 0.27], P = 0.005). Discussion. For individuals with AR, ILIT is safe and effective. ILIT alleviates clinical symptoms and reduces pharmaceutical consumption without causing severe AEs. However, the validity of this study is compromised by the substantial heterogeneity and risk of bias in the included researches. RegistrationCRD42022355329. [ABSTRACT FROM AUTHOR]

Background. Subcutaneous immunotherapy (SCIT) is an effective therapy for allergic rhinitis (AR), but some AR patients still do not benefit from it. Nasal nitric oxide (nNO) and inducible nitric oxide synthase (iNOS/NOS2) act important roles in AR. This study aims to explore the abilities of serum NOS2 and nNO in predicting the clinical efficacy of SCIT in AR patients. Methods. We recruited 40 healthy controls (HCs) and 120 AR patients in this study. Serum NOS2 and nNO levels were compared between the two groups. In the AR group, patients underwent and finished 1-year of SCIT, and divided into the effective and ineffective groups, and the relationships between serum NOS2 and nNO levels and efficacy of SCIT were evaluated. Results. The serum NOS2 and nNO levels were higher in AR patients than HCs. In the effective group, the serum NOS2 and nNO levels were increased than the ineffective group. ROC curves presented that a combination of serum NOS2 and nNO exhibited promising predictive ability in predicting the clinical efficacy of SCIT. Conclusions. Serum NOS2 and nNO levels were enhanced in AR patients and might affect the efficacy of SCIT. The combined use of serum NOS2 and nNO levels could be a reliable and useful method for predicting the clinical efficacy of SCIT. [ABSTRACT FROM AUTHOR]

The aim of this study was to identify differences in serum metabolomics profiles of house-dust-mite (HDM)-induced allergic rhinitis (AR) patients compared to controls and to explore novel biomarkers reflecting disease severity. Serum samples were collected from 29 healthy controls and HDM-induced 72 AR patients, including 30 mild patients (MAR) and 42 moderate to severe AR patients (MSAR). Metabolomics detection was performed, and orthogonal partial least square discriminate analysis was applied to assess the differences between AR patients and controls and for subgroups based on disease severity. These analysis results successfully revealed distinct metabolite signatures which distinguished MAR patients and MSAR patients from controls. MSAR patients also could be discriminated from MAR patients based on their metabolic fingerprints. Most observed metabolite changes were related to glycine, serine, and threonine metabolism, pyrimidine metabolism, sphingolipid metabolism, arginine and proline metabolism, and fatty acid metabolism. Levels of sarcosine, sphingosine-1-phosphate, cytidine, and linoleic acid significantly correlated with the total nasal symptom score and visual analogue scale in AR patients. These results suggest that metabolomics profiling may provide novel insights into the pathophysiological mechanisms of HDM-induced AR and contribute to its evaluation of disease severity. [ABSTRACT FROM AUTHOR]

The standard particle swarm optimization (PSO) algorithm is the boundary constraints of simple variables, which can hardly be directly applied in the constrained optimization. Furthermore, the standard PSO algorithm often fails to obtain the global optimal solution when the dimensionality is high for unconstrained optimization. Thus, an improved PSO-based extended domain method (IPSO-EDM) is proposed to solve engineering optimization problems. The core idea of this method is that the original feasible region is expanded in the constrained optimization which is transformed into the unconstrained optimization by combining the ergodicity of chaos optimization and the evolutionary variation to realize global search. In addition, to verify the effectiveness of the IPSO-EDM, an unconstrained optimization case study, four constrained optimization case studies, and one engineering example are investigated. The results indicate that the computational accuracy of the IPSO-EDM is comparable to that provided by the existing literature, and the computational efficiency of the IPSO-EDM is significantly improved. Meanwhile, this method has conspicuous global search ability and stability in engineering optimization. [ABSTRACT FROM AUTHOR]

Gastric cancer is the fifth most common malignancy all over the world, and the factors that can affect progress and prognosis of the gastric cancer patients are various, such as TNM stages, invasive depth, and lymph node metastasis ratio. T cell immunity is important component of human immunity system and immunity responding to tumor and dysfunction or imbalance of T cell immunity will lead to serious outcomes for body. T cell immunity includes many different types of cells, CD4+ T cell, CD8+ T cell, memory cell, and so on, and each of them has special function on antitumor response or tumor immune escape which is revealed in lung cancer, colorectal cancer, breast cancer, ovarian cancer, and so on. But its correlation with gastric cancer is not clear. Our review was preformed to explore the relationship between the progress and prognosis of gastric cancer (GC) and T cell immunity. According to recent researches, T cell immunity may have an important role in the progress and prognosis of GCs, but its function is affected by location, category, related molecule, and interaction between the cells, and some effects still are controversial. More researches are needed to clarify this correlation. [ABSTRACT FROM AUTHOR]