With the development of multichannel audio systems, corresponding audio quality assessment techniques, especially the objective prediction models, have received increasing attention. Existing methods, such as PEAQ(Per...With the development of multichannel audio systems, corresponding audio quality assessment techniques, especially the objective prediction models, have received increasing attention. Existing methods, such as PEAQ(Perceptual Evaluation of Audio Quality) recommended by ITU, usually lead to poor results when assessing multichannel audio, which have little correlation with subjective scores. In this paper, a novel two-layer model based on Multiple Linear Regression(MLR) and Neural Network(NN) is proposed. Through the first layer, two indicators of multichannel audio, Audio Quality Score(AQS) and Spatial Perception Score(SPS) are derived, and through the second layer the overall score is output. The final results show that this model can not only improve the correlation with the subjective test score by 30.7% and decrease the Root Mean Square Error(RMSE) by 44.6%, but also add two new indicators: AQS and SPS, which can help reflect the multichannel audio quality more clearly.展开更多
Background Atherosclerosis(AS)and tumours are the leading causes of death worldwide and share common risk factors,detection methods and molecular markers.Therefore,searching for serum markers shared by AS and tumours ...Background Atherosclerosis(AS)and tumours are the leading causes of death worldwide and share common risk factors,detection methods and molecular markers.Therefore,searching for serum markers shared by AS and tumours is beneficial to the early diagnosis of patients.Methods The sera of 23 patients with AS-related transient ischaemic attack were screened by serological identification of antigens through recombinant cDNA expression cloning(SEREX),and cDNA clones were identified.Pathway function enrichment analysis was performed on cDNA clones to identify their biological pathways and determine whether they were related to AS or tumours.Subsequently,gene–gene and protein–protein interactions were performed and AS-associated markers would be discovered.The expression of AS biomarkers in human normal organs and pan-cancer tumour tissues were explored.Then,immune infiltration level and tumour mutation burden of various immune cells were evaluated.Survival curves analysis could show the expression of AS markers in pan-cancer.Results AS-related sera were screened by SEREX,and 83 cDNA clones with high homology were obtained.Through functional enrichment analysis,it was found that their functions were closely related to AS and tumour functions.After multiple biological information interaction screening and the external cohort validating,poly(A)binding protein cytoplasmic 1(PABPC1)was found to be a potential AS biomarker.To assess whether PABPC1 was related to pan-cancer,its expression in different tumour pathological stages and ages was screened.Since AS-associated proteins were closely related to cancer immune infiltration,we investigated and found that PABPC1 had the same role in pan-cancer.Finally,analysis of Kaplan-Meier survival curves revealed that high PABPC1 expression in pan-cancer was associated with high risk of death.Conclusions Through the findings of SEREX and bioinformatics pan-cancer analysis,we concluded that PABPC1 might serve as a potential biomarker for the prediction and diagnosis of AS and pan-cancer.展开更多
基金supported by the National Natural Science Foundation of China (No.61571044,No.11590772,and No.61473041)
文摘With the development of multichannel audio systems, corresponding audio quality assessment techniques, especially the objective prediction models, have received increasing attention. Existing methods, such as PEAQ(Perceptual Evaluation of Audio Quality) recommended by ITU, usually lead to poor results when assessing multichannel audio, which have little correlation with subjective scores. In this paper, a novel two-layer model based on Multiple Linear Regression(MLR) and Neural Network(NN) is proposed. Through the first layer, two indicators of multichannel audio, Audio Quality Score(AQS) and Spatial Perception Score(SPS) are derived, and through the second layer the overall score is output. The final results show that this model can not only improve the correlation with the subjective test score by 30.7% and decrease the Root Mean Square Error(RMSE) by 44.6%, but also add two new indicators: AQS and SPS, which can help reflect the multichannel audio quality more clearly.
基金funded by National Natural Science Foundation of China(82071340)Science and Technology Project of Guangzhou,China(202201020027)+1 种基金National Foreign Expert Project of the Ministry of Science and Technology(G20200019047)Science and Technology Planning Project of Guangdong Province,China(2021A1313030052,2022A0505050041).
文摘Background Atherosclerosis(AS)and tumours are the leading causes of death worldwide and share common risk factors,detection methods and molecular markers.Therefore,searching for serum markers shared by AS and tumours is beneficial to the early diagnosis of patients.Methods The sera of 23 patients with AS-related transient ischaemic attack were screened by serological identification of antigens through recombinant cDNA expression cloning(SEREX),and cDNA clones were identified.Pathway function enrichment analysis was performed on cDNA clones to identify their biological pathways and determine whether they were related to AS or tumours.Subsequently,gene–gene and protein–protein interactions were performed and AS-associated markers would be discovered.The expression of AS biomarkers in human normal organs and pan-cancer tumour tissues were explored.Then,immune infiltration level and tumour mutation burden of various immune cells were evaluated.Survival curves analysis could show the expression of AS markers in pan-cancer.Results AS-related sera were screened by SEREX,and 83 cDNA clones with high homology were obtained.Through functional enrichment analysis,it was found that their functions were closely related to AS and tumour functions.After multiple biological information interaction screening and the external cohort validating,poly(A)binding protein cytoplasmic 1(PABPC1)was found to be a potential AS biomarker.To assess whether PABPC1 was related to pan-cancer,its expression in different tumour pathological stages and ages was screened.Since AS-associated proteins were closely related to cancer immune infiltration,we investigated and found that PABPC1 had the same role in pan-cancer.Finally,analysis of Kaplan-Meier survival curves revealed that high PABPC1 expression in pan-cancer was associated with high risk of death.Conclusions Through the findings of SEREX and bioinformatics pan-cancer analysis,we concluded that PABPC1 might serve as a potential biomarker for the prediction and diagnosis of AS and pan-cancer.
