基于DCNN网络及Self-Attention-BiGRU机制的轴承剩余寿命预测

深度神经网络在剩余寿命预测(RUL)领域得到了广泛的应用。传统的滚动轴承寿命预测模型存在预测精确度较低、鲁棒性较弱的问题。为了进一步提升预测模型的精确度以及鲁棒性,提出了一种融合深度卷积神经网络(DCNN)、双向门控循环单元(BiGRU)以及自注意力机制(Self-Attention)三种模块的滚动轴承剩余使用寿命预测模型。首先,利用DCNN网络对原始振动信号的时域特征、频域特征进行了提取;然后,使用不确定量化的方法对提取到的特征进行了评价和筛选,利用筛选过后的特征构建了新的替代特征集;最后,利用Self-Attention-BiGRU网络对轴承的剩余使用寿命进行了预测,并在IEEE PHM2012数据集上进行了验证。实验结果表明:相较于BiGRU、GRU和BiLSTM三种模型的预测结果,基于DCNN及Self-Attention-BiGRU方法的预测结果最优,两项误差值:平均绝对误差(MAE)、均方根误差(RMSE)最低,其中工况一的一号轴承RUL预测的MAE值相较于BiGRU、GRU以及BiLSTM网络分别下降了7.0%、7.4%和6.5%,RMSE值相较于其他三种模型分别下降了7.6%、8.4%和6.9%,预测的Score值最高,分值为0.985。通过不同数据集的划分,证明了该方法在轴承RUL预测时的强鲁棒性。实验结果验证了基于DCNN网络及Self-Attention-BiGRU模型在轴承剩余使用寿命预测中的有效性。

基于BERT-SELFATT-CNN模型的垃圾邮件分类方法

针对传统垃圾邮件分类方法中使用静态词向量不能解决一词多义、长序列信息特征提取不足等问题,提出了一种基于BERT-SELFATT-CNN模型的垃圾邮件分类方法。使用动态文本表示方法BERT对邮件内容进行预训练,并生成带有上下语义信息的词向量,经过能够并行计算的自注意力机制层计算词与词之间的相似度去挖掘句子长距离信息,将生成的隐藏层向量输入到CNN网络提取向量局部特征。在中文垃圾邮件数据集上与已有模型进行对比实验,结果表明该模型在精确度、召回率和F1值上均有提高,模型训练速度也得到提升。

Effect of Diabetes Self-Management Education on Glycaemic Control in Sudanese Adults with Type 2 Diabetes

Research Background: The high prevalence of diabetes in Sudan, estimated at 16%, highlights the importance of effective health education in diabetes management. Diabetes self-management education has been identified as a crucial tool in enhancing the knowledge, attitudes, and abilities necessary for self-management among individuals with diabetes. Aim: To assess the impact of diabetes self-management education on medication adherence and glycemic control in Sudanese adults with type 2 diabetes before and 3 months after the DSME intervention. Method: The study was conducted in Sudan between September 2022 and March 2023, it was an interventional, one-group, pre- and post-test study that aimed to assess the impact of diabetes self-management education (DSME) on medication adherence and diabetes control in Sudanese adults with type 2 diabetes. The research was conducted in primary health care centers in six cities in Sudan and involved 244 participants. The data entry and statistical analysis were conducted using the Statistical Package for Social Sciences version 27.0. A paired t test was used for analysis. Results: The study included 244 participants, 67% of whom were males. The age mean ± SD was 48.6 ± 9.3 years, and 85.3% of participants were married. Age at onset of diabetes mean ± SD was 40.60 ± 7.81 years;44.6% had diabetes for less than 5 years;and 84.1% had a positive family history of diabetes mellitus. The levels of poor, low, and partial adherence to medication decreased by 8.2%, 4%, and 20.6%, respectively, after the intervention. The levels of good and high medication regime adherence increased by 13% and 19.8%, respectively;BMI decreased by 1.1 ± 0.73 kg/m2 (p = 0.005). The fasting blood sugar decreased by 69 ± 32.9 mg/dl (p = 0.049), and the glycated hemoglobin decreased by 1.21 ± 0.28% (p = 0.001). Conclusions: The findings of this study reinforce the importance of patient education in improving glycemic control and enhancing self-management behaviors. Patient education plays a critical role in enhancing glycemic control and self-management behaviors. It is essential for healthcare providers to adopt a patient-centered approach, taking into account the individual's beliefs, attitudes, and knowledge about their illness and treatment. Overcoming these challenges necessitates a comprehensive approach, including enhancing healthcare professionals’ knowledge and communication skills, offering accessible and culturally sensitive diabetes education programs, and addressing barriers to resources and support for self-management.

Research Progress on Self-Efficacy Level of Patients with Type 2 Diabetes Mellitus and Its Influencing Factors

Self-efficacy plays an important role in the management of type 2 diabetes mellitus (T2DM) patients, and it runs through the whole process of diabetes treatment, which is conducive to controlling and delaying the occurrence and development of complications, as well as improving the quality of life of patients. This paper mainly describes the concept of self-efficacy, the current situation of self-efficacy of diabetic patients at home and abroad, the functional aspects and their influencing factors, so as to take relevant measures on how to improve self-efficacy. It aims to provide a theoretical basis for the development of self-efficacy interventions for patients with type 2 diabetes mellitus.

Practice of Glycemic Self-Monitoring in Diabetic Patients Followed at the Endocrinology Department of Donka University Hospital in Guinea

Diabetes is a chronic pathology whose evolution is marked by micro and macroangiopathic complications. Optimal management can prevent the onset of complications and improve patients’ quality of life. Objectives: To determine the frequency of self-monitoring of blood glucose and to describe the errors found during self-monitoring in diabetic patients followed at the Endocrinology Department of Donka University Hospital in Guinea. Materials and methods: Descriptive cross-sectional study carried out between August and September 2020 involving diabetic patients followed up at the Endocrinology and Diabetology Department of the Donka National Hospital, CHU Conakry. Results: A total of 301 patients were enrolled, with an average age of 44.24 ± 21.01 years. 64.12% were female. Type 2 diabetes predominated in 64% of cases. The mean duration of diabetes was 6.14 ± 4.67 years, and 75.08% of patients lived in urban areas. Patients were on insulin in 36.21% of cases, insulin and biguanides (26.25%), hypoglycemic sulfonamide and biguanides (19.27%) and biguanides in 18.27% of cases. The frequency of self-monitoring of blood glucose was 43%, and 38% of patients made errors, notably reusing lancets (60%), not checking the expiration date (55.65%) and not washing their hands (48%). Conclusion: This study shows that self-monitoring of blood glucose is not performed by the majority of patients. Numerous errors were identified during blood glucose testing. Continued therapeutic education on the use of blood glucose meters will help empower patients and improve their quality of life.

Decision-Making and Management of Self-Care in Persons with Traumatic Spinal Cord Injuries: A Preliminary Study

Patients and physicians understand the importance of self-care following spinal cord injury (SCI), yet many individuals with SCI do not adhere to recommended self-care activities despite logistical supports. Neurobehavioral determinants of SCI self-care behavior, such as impulsivity, are not widely studied, yet understanding them could inform efforts to improve SCI self-care. We explored associations between impulsivity and self-care in an observational study of 35 US adults age 18 - 50 who had traumatic SCI with paraplegia at least six months before assessment. The primary outcome measure was self-reported self-care. In LASSO regression models that included all neurobehavioral measures and demographics as predictors of self-care, dispositional measures of greater impulsivity (negative urgency, lack of premeditation, lack of perseverance), and reduced mindfulness were associated with reduced self-care. Outcome (magnitude) sensitivity, a latent decision-making parameter derived from computationally modeling successive choices in a gambling task, was also associated with self-care behavior. These results are preliminary;more research is needed to demonstrate the utility of these findings in clinical settings. Information about associations between impulsivity and poor self-care in people with SCI could guide the development of interventions to improve SCI self-care and help patients with elevated risks related to self-care and secondary health conditions.

Unified Description of the Three Stable Particles in Self-Action Allows Determination of Their Relative Masses

The Dirac equation γμ(δμ-eAμ)Ψ=mc2Ψ describes the bound states of the electron under the action of external potentials, Aμ. We assumed that the fundamental form of the Dirac equation γμ(δμ-Sμ)Ψ=0 should describe the stable particles (the electron, the proton and the dark-matter-particle (dmp)) bound to themselves under the action of their own potentials Sμ. The new equation reveals that self energy is consequence of self action, it also reveals that the spin angular momentum is consequence of the dynamic structure of the stable particles. The quantitative results are the determination of their relative masses as well as the determination of the electromagnetic coupling constant.

The Impact of Simulation Education on Self-Efficacy in Pre-Registration Nursing Students

This literature review primarily aims to explore and synthesise the previous studies in simulation education research conducted over the past five years related to the effects of simulation training on the self-efficacy of undergraduate pre-registration nursing students. The second aim of this study is to explore additional outcome variables that were examined in the previous studies. Five electronic databases were searched systematically. These databases were MEDLINE, CINAHL Plus, Scopus, Embase and PsycINFO. The PICO model was employed to identify the search terms, with a thesaurus being used to provide synonyms. Reference lists of relevant articles were examined and hand searches of journals were also undertaken. The quality of each study was assessed using the Simulation Research Rubric (SRR). A total of 11 studies were included. All studies explored the impact of simulation education on undergraduate pre-registration nursing. Six studies explored nursing students’ competence and performance and two papers examined their critical thinking. Problem solving, learning motivation, communication skills and knowledge acquisition were examined once. The majority of studies indicated that simulation training has a positive impact on pre-registration nursing students’ self-efficacy and other outcome variables. Furthermore, the study results indicate that simulation training is more dependable than traditional training, and students were extremely satisfied with the simulation training. However, most of the studies included in this review had several gaps, including study design, sample size and dissimilarities between the scales used. Further research with large samples, reliable and valid instruments, and outcomes measures (such as critical thinking and transferability of skills) is required to provide better insight into the effectiveness of simulation in undergraduate nursing education. .

Edge-Federated Self-Supervised Communication Optimization Framework Based on Sparsification and Quantization Compression

The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning being difficult to process large-scale unlabeled data. The existing federated self-supervision framework has problems with low communication efficiency and high communication delay between clients and central servers. Therefore, we added edge servers to the federated self-supervision framework to reduce the pressure on the central server caused by frequent communication between both ends. A communication compression scheme using gradient quantization and sparsification was proposed to optimize the communication of the entire framework, and the algorithm of the sparse communication compression module was improved. Experiments have proved that the learning rate changes of the improved sparse communication compression module are smoother and more stable. Our communication compression scheme effectively reduced the overall communication overhead.

Three-Dimensional Multi-Phase Microscopic Simulation of Service Life of Recycled Large Aggregate Self-Compacting Concrete

Recycled large aggregate self-compacting concrete (RLA-SCC) within multiple weak areas. These weak areas have poor resistance to chloride ion erosion, which affects the service life of RLA-SCC in the marine environment. A three-dimensional multi-phase mesoscopic numerical model of RLA-SCC was established to simulate the chloride ions transportation in concrete. Experiments of RLA-SCC immersing in chloride solution were carried out to verify the simulation results. The effects of recycled large aggregate (RLA) content and RLA particle size on the service life of concrete were explored. The results indicate that the mesoscopic numerical simulation results are in good agreement with the experimental results. At the same depth, the closer to the surface of the RLA, the greater the chloride ion concentration. The service life of RLA-SCC in marine environment decreases with the increase of RLA content. Compared with the service life of 20% content, the service life of 25% and 30% content decreased by 20% and 42% respectively. Increasing the particle size of RLA can effectively improve the service life of RLA-SCC in chloride environment. Compared with the service life of 50 mm particle size, the service life of 70 mm and 90 mm increased by 61% and 163%, respectively. .

联合Self-attention与Axial-attention的机场跑道裂缝分割

机场跑道裂缝形态多样、方向各异、长短不一且粗细不均,通常不具有统计规律。现有的各类裂缝分割算法难以在此类复杂场景中落地。针对上述问题,提出了联合self-attention与axial-attention的机场跑道裂缝分割网络(CSA-net),通过引入自注意力模块、轴向注意力模块、可变形卷积模块,提取裂缝的局部特征和全局语义特征。通过transformer decoder还原特征图的原始尺寸,融合了不同尺度间的分割结果,保留尽可能多的细节信息,使得CSA-net有更好的分割精度。在机场跑道实拍的数据集上进行的测试表明,针对裂缝的像素级分割指标F1-score达到了78.91%,高于目前各类裂缝分割算法。

基于并行CNN-Self attention&LSTM的锂电池RUL间接预测

针对锂离子电池难以在线测量直接健康因子(容量、内阻)进行剩余使用寿命(RUL)预测的现状,提出基于并行CNN-Self attention与LSTM组合的锂电池RUL间接预测方法。首先基于锂离子电池放电循环数据,利用灰度关联分析筛选出能够高度体现电池容量衰减的间接健康因子;然后分别对间接健康因子使用卷积神经网络(CNN)进行特征提取和自注意力机制(Self attention)调整特征权重得到对应的特征矩阵;最后融合特征矩阵,并使用长短期记忆(LSTM)网络进行锂电池RUL预测。使用NASA锂离子电池数据集进行实验,结果表明:与传统的CNN、LSTM和CNN-LSTM模型相比,并行CNN-Self attention&LSTM模型所得到的容量衰减曲线更接近实际容量衰减曲线,误差波动范围更小,在RMSE、MAE和R2系数3种评价指标上表现更优。

结合LSTM和Self‑Attention的滚动轴承剩余使用寿命预测方法

为了构建准确表征滚动轴承退化过程的趋势性健康度指标,提高滚动轴承剩余使用寿命(Remaining Useful Life,RUL)的预测精度,提出了一种结合长短期记忆(Long‑Short Term Memory,LSTM)和自注意力(Self‑Attention)机制的神经网络模型(LSTM‑SA)用于滚动轴承RUL预测。利用包络解调获得原始信号的包络谱,再将包络谱分段并计算对应频段的皮尔逊相关系数,得到具有单调性和趋势性的退化特征;将退化特征归一化处理后作为LSTM‑SA模型的输入,并利用LSTM自适应提取退化特征时间上的内部相关性以及Self‑Attention对关键信息的筛选,消除无用信息的干扰,挖掘深层次特征,构建健康度指标并得到退化曲线;确定失效阈值,利用最小二乘法拟合退化曲线,预测寿命失效点,实现滚动轴承的RUL预测。在PHM2012数据集上的实验结果表明,所提出的方法相比于其他文献,平均绝对误差分别降低了43.18%,62.57%和59.44%,平均得分分别提高了10.87%,45.71%和34.21%;在工程实际数据中的实验结果表明,所提出方法的平均预测误差分别比Standard‑RNN和CNN方法降低了39.58%和74.86%。

基于改进Self-paced Ensemble算法的浏览器指纹识别

浏览器指纹技术凭借其无状态、跨域一致等优点,已经被许多网站应用到用户追踪、广告投放和安全验证等方面。浏览器指纹识别的过程是典型的不平衡数据的分类过程。针对当前浏览器指纹长期追踪过程中存在数据样本类不平衡导致指纹识别准确度低、长期追踪易失效等问题,提出了改进的Self-paced Ensemble(Improved SPE,ISPE)方法应用于浏览器指纹识别。对浏览器指纹样本欠采样过程和集成学习单个分类器的训练过程进行了改进,重点针对难以识别的浏览器指纹,添加类注意力机制并优化自协调因子,使分类器在训练和识别浏览器指纹的过程中更加注重边界样本的分类效果,从而提升总体的浏览器指纹识别准确度。在所收集的3 483条指纹和开源数据集中的15 000条指纹上进行了实验,结果表明,ISPE算法在浏览器指纹匹配识别的F1-score达到95.6%,相比Bi-RNN算法提高了16.8%。

校园欺凌现象中家长角色的负面影响及其矫正——基于自我心像(self-image)分析的视角

校园欺凌事件的发生与家长角色的负面影响有着深刻的关联。造成负面影响的家长角色,在亲子关系中主要表现为专制者、臣服者、冷漠者三种,在亲朋关系中主要表现为征服者与被征服者、妥协者和旁观者。这些角色属于潜在的“精神暗能”,会在无形中影响孩子美好的自我心像的塑造,如果不断“层累”,则会导致孩子损己害人的攻击性、破坏性、自伤性事件发生。因此,家长应不断反躬自省、慎独自律、明德积学,学会民主有效地沟通,完善自我心像,给孩子以情感的关怀、行为的示范、思想的引领,与学校教育和社会教育形成真正意义上的合力,从心像塑造的源头上防范校园欺凌现象的发生,或将已发生的校园欺凌的负面影响降到最低。

Ext-ICAS:A Novel Self-Normalized Extractive Intra Cosine Attention Similarity Summarization

With the continuous growth of online news articles,there arises the necessity for an efficient abstractive summarization technique for the problem of information overloading.Abstractive summarization is highly complex and requires a deeper understanding and proper reasoning to come up with its own summary outline.Abstractive summarization task is framed as seq2seq modeling.Existing seq2seq methods perform better on short sequences;however,for long sequences,the performance degrades due to high computation and hence a two-phase self-normalized deep neural document summarization model consisting of improvised extractive cosine normalization and seq2seq abstractive phases has been proposed in this paper.The novelty is to parallelize the sequence computation training by incorporating feed-forward,the self-normalized neural network in the Extractive phase using Intra Cosine Attention Similarity(Ext-ICAS)with sentence dependency position.Also,it does not require any normalization technique explicitly.Our proposed abstractive Bidirectional Long Short Term Memory(Bi-LSTM)encoder sequence model performs better than the Bidirectional Gated Recurrent Unit(Bi-GRU)encoder with minimum training loss and with fast convergence.The proposed model was evaluated on the Cable News Network(CNN)/Daily Mail dataset and an average rouge score of 0.435 was achieved also computational training in the extractive phase was reduced by 59%with an average number of similarity computations.

心理弹性在老年慢性疼痛患者疼痛管理自我效能与生活质量间的中介效应

目的 探讨心理弹性在老年慢性疼痛患者疼痛管理自我效能与生活质量间的中介效应。方法 2021年1月至12月采用方便抽样法选取在南京大学医学院附属鼓楼医院就诊的老年慢性疼痛患者96例为研究对象,应用心理弹性量表、疼痛管理自我效能量表及老年生活质量评定表对入组患者进行调查,采用Bootstrap法行中介效果验证。结果 老年慢性疼痛患者心理弹性与疼痛自我管理效能及生活质量呈正相关(r=0.456、0.478,P<0.05)。心理弹性在老年慢性疼痛患者疼痛自我管理效能及生活质量间存在部分中介效应,占总效应52.1%。结论 老年慢性疼痛患者心理弹性及疼痛自我管理水平处于中等偏低,生活质量还有待提高。心理弹性水平可影响老年慢性疼痛患者疼痛管理自我效能及生活质量,建议医院、社区及家庭可给予患者鼓励及支持,以增强患者心理弹性,提高患者疼痛管理自我效能,提高患者生活质量。

虚拟现实技术在成人心肺复苏培训中应用的范围综述

目的对虚拟现实(virtual reality,VR)技术在成人心肺复苏(cardiopulmonary resuscitation,CPR)培训中的应用进行范围审查,以识别VR技术干预的内容要素和应用效果。方法以乔安娜布里格斯研究所范围综述指南为方法学框架,检索PubMed、Embase、CINAHL、Web of Science、Cochrane Library、中国知网、万方和中国生物医学文献数据库,检索时限为建库至2023年8月31日,对纳入文献进行汇总和分析。结果共纳入15篇文献,VR技术干预的内容要素包括实施CPR的意愿、反应、自我效能、按压频率、按压深度、无血流时间、复训时间、时间成本;结局指标类型为心理指标、胸外按压的质量指标、经济指标。结论VR技术在成人CPR培训中具有良好的应用前景,在心理、胸外按压质量、经济等方面的效果还可进一步挖掘。未来可基于面对面培训联合数字化反馈装置,最大化发挥VR技术的优势,形成一套综合干预策略和创新的培训模式,以进一步提高CPR培训的整体成效。

Comparison of Self-Perception of Esthetics and Orthodontic Treatment Needs among Dental and Non-Dental Students with Assessment by Orthodontist

Objectives: The present study was conducted to compare the self-perception of esthetics and wish for seeking orthodontic treatment among dental and non-dental students. The realistic orthodontic treatment needs were confirmed by expert orthodontist. Methods: A cross-sectional study was conducted among 255 male students (Dental—75, Medical—93 and Pharmacy—87 students). The questionnaire included 20 items covering dental esthetics self-perception (10 questions), self-confidence and psychological impact (5 questions), and the need for seeking orthodontic treatment (5 questions) on a five-point Likert scale. The realistic orthodontic treatment needs were confirmed by photographs using aesthetic component of IOTN and clinical examination for the participants and analysis of jaw models using Dental aesthetic index (DAI). Kruskal-Wallis ANOVA was used to check the significant difference between groups. Results: The overall average esthetic self-perception score for total sample was 3.83. The overall average psychological impact score for the whole sample was 2.67. The total percentage of participants who either agree or strongly agree with the question related to their perception of need for seeking orthodontic treatment was 70%. According to the assessment of orthodontic needs using AC-IOTN, 19.8% required definitive treatment. According to the assessment of orthodontic treatment needs based on DAI, 20.3% and 9.9% needed highly desirable (DAI 31 - 35) and definite need of treatment (DAI ≥ 36) respectively. Conclusion: It can be concluded that there was no difference between the esthetic perception of dental and non-dental students. The self-perception for seeking orthodontic treatment was over-reported by participants compared to real requirement as assessed by orthodontic specialist. Dental esthetics has no psychological impact on academic performance and self-confidence as perceived by study participants.

Information Needs and Self-Care Practices of Diabetic Patients in Mbala, Northern Province, Zambia

Introduction: Diabetes mellitus (DM) is a chronic disease that occurs either when the pancreas does not produce enough insulin or when the body cannot effectively use the insulin it produces. It is “a group of metabolic diseases characterized by hyperglycemia resulting from defects in insulin secretion, insulin action or both” manifested by carbohydrates, fat and protein metabolism abnormality. If untreated high blood sugar can damage the nerves, eyes, kidneys, and other organs. The purpose of this study was to assess the information needs and self-care practice of Diabetic Patients in Mbala, Northern Province Zambia. Methods: This was an analytical cross-sectional study where 105 respondents aged 18 years and above participated in the study. Participants were randomly selected. A structured interview schedule and a check list were used to collect data. Statistics Package for Social Sciences computer software package version 23.0 was used to analyze data. Chi square and fisher’s exact tests were used to test the significance of the association between Knowledge of Diabetes Mellitus, attitude towards self-care practices, self-care practices among Diabetic patients and the need for information among Diabetic patients. A 95% confidence interval and P value of 0.05 were used to ascertain the degree of significance. Multi-variate binary logistic regression model to determine predictors of self-care practices and need for information was also used. Result: On analyzing the dependent variables, more than half (61.9%), had high need for information and three quarters (85.7%) of respondents had poor self-care practices. Slightly more than half (58.1%) had high knowledge levels majority (78.1%), had a negative attitude. Significant associations were found P Conclusion: Negative attitudes and lack of information among Diabetic patients were the main reasons associated with poor self-care practices. Particular attention should therefore be given to ensuring that Diabetic patients are given adequate information on Diabetes self-care in order to improve the quality of life.