JLJiajia Li

Jiajia Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jiajia Li has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Improving Monaural Speech Enhancement with Dynamic Scene Perception Module

    by Tian Lan, Jiajia Li, Wenxin Tai, Cong Chen, Jun Kang, Qiao Liu

    Speech enhancement aims to recover clean speech from complex noise backgrounds. This paper proposes a novel information processing module dubbed dynamic scene perception module (DSPM) that can help existing systems to accommodate various complex scenarios. The inspiration of DSPM is based on the observation that different regions of the noisy spectrum in different scenarios have different enhancing requirements. Concretely, DSPM consists of two parts, one for dynamic scene estimation, and the other for adaptive region perception. In particular, the scene estimator utilizes a spectrum-energy-based attention mechanism to obtain the coefficients of each convolution kernel. Then, at each position’ the region perceptron chooses the corresponding kernels by considering the requirements of the current region (preserve vocals or suppress noise). Systematic evaluations on the TIMIT corpus and Voice Bank + DEMAND demonstrate the effectiveness of our method. Compared with the existing systems, our proposed method achieved better performance under various SNR conditions and complex noise scenarios.

  • Open Access

    Qualitative Study on Male Nursing Students’ Cognition of Nine-Valent Preventive Vaccine

    by Tiantian Jia, Junjuan Zhang, Jiajia Li, Lilu Tian, Yufeng Liu, Wenjing Yu, Ruijuan Han

    Objective: To investigate the cognition degree of male nursing students to HPV and nine-valent vaccine and the influencing factors of male willingness to receive nine-valent HPV vaccine. Methods: Qualitative research semi-structured interview was conducted on male nursing students, and phenomenological research method was used to record, ran scribe, encode and classify the interview data and extract the topic. The number of interviews was determined according to the information saturation. Results: Seven themes were summarized in this study, which were mainly divided into two aspects. The promotion of vaccination includes two aspects: self-benefit and benefit of others. The prevention of vaccination mainly includes low awareness rate, feminization of vaccine information, high cost and safety and effectiveness. Conclusion: Male nursing students have low cognition degree and inoculation intention to human papillomavirus and nine-valent vaccine, so it is necessary to further strengthen publicity and carry out college education to improve vaccination.

  • Open Access

    A Study of the Relationship between the Polymorphism and Mutation of rs682429 and rs3781590 in the LRP5 Gene and Bone Metabolism in Postmenopausal Type 2 Diabetic Women in Xinjiang

    by Jun Li, SiYuan Li, HuiRong Zhao, JiaJia Li, Shuang Wang, YanQiu Shi

    Objective. To explore the expression of the polymorphism and mutation of rs682429 and rs3781590 in the low-density lipoprotein receptor-related protein 5 (LRP5) genotype and to analyse the relationship of bone mineral density (BMD) and bone metabolism markers in postmenopausal women with type-2 diabetes mellitus (T2DM) in Xinjiang, China, to provide a basis for prevention and treatment of the disease. Methods. A total of 136 postmenopausal women were included in the study. According to the results of an oral glucose tolerance test (OGTT) and dual-energy X-ray (DEXA) determination of BMD, the study subjects were divided into 4 groups: group A: normal OGTT+normal bone mass group; group B: normal OGTT+osteoporotic (OP) group; group C: T2DM+normal bone mass group; group D: T2DM+osteoporotic (OP) group. Calcium (Ca), phosphorus (P), alkaline phosphatase (ALP), and clinical biochemical data were determined; haemoglobin A1c (HbA1c) was measured by HPLC; BMD of the femoral neck, hip, and lumbar spine (L1-4) was measured by dual-energy X-ray (DEXA); and the rs682429 and rs3781590 polymorphisms of the LRP5 gene were detected by time-of-flight mass spectrometry (TOF MS). Results. (1) The rs682429 polymorphism of the LRP5 genotype distribution was statistically significant (P<0.05) in group B compared with group A. (2) The triglycerides (TG) of women with the CT/TT genotype (mutant type) were higher than those of women with the CC genotype (wild type) (2.37±1.30 vs. 1.52±0.83, P<0.05) at the rs3781590 site of the LRP5 gene in group D. (3) Multiple linear regression analysis showed that TG (β=0.034, P<0.05) and body mass index (BMI) (β=0.013, P<0.05) were the influencing factors of BMD (L1-4) in T2DM patients. TG (β=0.022, P<0.05), BMI (β=0.009, P<0.05), and duration of menopause (β=0.005, P<0.05) were the influencing factors of BMD (hip). Conclusion. (1) The rs682429 polymorphism site in the LRP5 gene may be involved in bone metabolism in postmenopausal women from Xinjiang. (2) The rs3781590 mutation in the LRP5 gene from these subjects may be involved in lipid metabolism. (3) Among postmenopausal women with type 2 diabetes mellitus and bone mass abnormality in the Xinjiang Shihezi area, high BMI and TG are protective factors against increased BMD. Duration of menopause is a risk factor for increased BMD.


  • Computer-Aided Diagnosis and Clinical Trials of Cardiovascular Diseases Based on Artificial Intelligence Technologies for Risk-Early Warning Model

    by Bin Li, Shuai Ding, Guolei Song, Jiajia Li, Qian Zhang

    The use of artificial intelligence in medicine is currently an issue of great interest, especially with regard to the diagnostic or predictive analysis of medical data. In order to achieve the regional medical and public health data analysis through artificial intelligence technologies, spark data analysis is adopted as the research platform for hypertension patients, and artificial intelligence technologies are used to preprocess the data with inconsistency, redundancy, incompleteness, noise and error; Aiming at the unbalanced data sets, the Z-score standard is adopted to convert data into usable form suitable for data mining. And, the application of Logistic, Naive Bayesian regression, and support vector machine based on three groups of different prognosis in severe cases, including stroke, heart failure and renal failure symptoms, establish the risk early warning model for 3 years time. In addition, to select the optimal feature subset based on medicine big-data features, the model simplification and optimization are done in training process, the experimental results show that the feature subset selection can ensure the classification performance similar to the clinical features of the model. Therefore, according to chronic cardiovascular disease, acute cardiovascular events and cardiovascular events caused by critical illness events, we screen out the relevant prognosis of serious illness (stroke, heart failure, renal failure), which is related to the prognosis of serious illness. Targeted prevention has a guiding role and practical significance according to the results of artificial intelligence analysis.