Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 3.815
Filtrar
1.
Health Aff (Millwood) ; 41(2): 296-303, 2022 02.
Artigo em Inglês | MEDLINE | ID: mdl-35130076

RESUMO

The Asian American health narrative reflects a long history of structural racism in the US and the complex interplay of racialized history, immigrant patterns, and policies regarding Asians in the US. Yet owing to systematic issues in data collection including missing or misclassified data for Asian Americans and practices that lead to indiscriminate grouping of unlike individuals (for example, Chinese, Vietnamese, and Bangladeshi) together in data systems and pervasive stereotypes of Asian Americans, the drivers and experiences of health disparities experienced by these diverse groups remain unclear. The perpetual exclusion and misrepresentation of Asian American experiences in health research is exacerbated by three racialized stereotypes-the model minority, healthy immigrant effect, and perpetual foreigner-that fuel scientific and societal perceptions that Asian Americans do not experience health disparities. This codifies racist biases against the Asian American population in a mutually reinforcing cycle. In this article we describe the poor-quality data infrastructure and biases on the part of researchers and public health professionals, and we highlight examples from the health disparities literature. We provide recommendations on how to implement systems-level change and educational reform to infuse racial equity in future policy and practice for Asian American communities.


Assuntos
Americanos Asiáticos , Emigrantes e Imigrantes , Confiabilidade dos Dados , Humanos , Grupos Minoritários
2.
Glob Health Res Policy ; 7(1): 24, 2022 Jul 19.
Artigo em Inglês | MEDLINE | ID: mdl-35854338

RESUMO

BACKGROUND: Cerebral palsy (CP) registers serve as instrumental tools to support development of care pathways, preventative strategies, and health gains. Such health gains, however, are not always universal, with Indigenous health inequities common. To support Indigenous health, health registers need complete, consistent, and high-quality data. The aim of this study was to identify perceived barriers to the ascertainment of Indigenous peoples on health registers and to collate strategies supporting comprehensive ascertainment and achievement of high-quality Indigenous data. METHODS: Environmental scanning methods were utilized within a Kaupapa Maori theoretical framework, which aims to produce research that is transformational and supportive of Indigenous health gain. Knowledge and insights were obtained from CP registers in countries with Indigenous populations and complemented by information from health registers in Aotearoa New Zealand (NZ). Data collection methods included an online survey and scan of organizational websites. Data extraction focused on general information about the register, barriers to ascertainment, and strategies to support ascertainment and high data quality. RESULTS: 52 registers were identified, 20 completed the survey and 19 included in the study (CP registers, n = 10, NZ health registers, n = 9). Web scan data were included for the other 32 registers (CP registers, n = 21, NZ health registers, n = 11). Indigenous health equity was identified in the visions and aims of only two health registers. Ethnicity data collection was identified in nearly three quarters of survey respondents and a limited number of organizational websites. Over half of survey respondents described system, health provider/service, or workforce barriers to ascertainment. Strategies were categorized into collaboration, health provider/service, workforce, and systems-levels. Indigenous-specific strategies were limited and focused on personal behaviour and access to registration. CONCLUSIONS: CP and other health registers can have a significant role in identifying and addressing Indigenous health inequities. However, this is not currently an overt priority for many registers in this study and few registers describe ascertainment and data quality strategies specific to Indigenous peoples. Significant opportunity exists for health registers to be accountable and to implement approaches to support Indigenous health equity, address structural determinants of inequities, and achieve health gain for all.


Assuntos
Equidade em Saúde , Confiabilidade dos Dados , Humanos , Povos Indígenas , Havaiano Nativo ou Outro Ilhéu do Pacífico , Grupos Populacionais
3.
AMIA Annu Symp Proc ; 2022: 293-302, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35854717

RESUMO

Clinical and translational research centers (CTRCs) have emerged as key centers for electronic medical record related research through integrated data repositories (IDRs) and the 'secondary use' of clinical data. Researchers accessing and pre-processing ever increasing amounts of electronic medical records for data mining tasks have a growing need for best practice approaches for clinical data quality assessment and improvement. This project focused on a large data extract for 7 statin medication prescriptions for patients with cardiovascular disease. After the initial data extraction, we proceeded to analyze the data for completeness, correctness, currency, and percentage populated using established data quality frameworks. Assessment of the said data was performed through medication possession ratios, medication discontinuation reasons, and drug dosages. When we compared distributions of data elements such as drug dosage before and after changes were introduced by our pre-processing protocols, only a minimal noticeable difference was found as the clinical data cohort quality assessment and pre-processing were completed without substantially altering the original data structure. Our study demonstrated practical steps for clinical data cohort quality improvement using medication data and illustrates a best practice approach in clinical data cohort quality improvement for any data mining tasks.


Assuntos
Registros Eletrônicos de Saúde , Melhoria de Qualidade , Estudos de Coortes , Confiabilidade dos Dados , Prescrições de Medicamentos , Humanos
4.
AMIA Annu Symp Proc ; 2022: 186-195, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35854725

RESUMO

The All of Us (AoU) Research Program aggregates electronic health records (EHR) data from 300,00+ participants spanning 50+ distinct data sites. The diversity and size of AoU's data network result in multifaceted obstacles to data integration that may undermine the usability of patient EHR. Consequently, the AoU team implemented data quality tools to regularly evaluate and communicate EHR data quality issues at scale. The use of systematic feedback and educational tools ultimately increased site engagement and led to quantitative improvements in EHR quality as measured by program- and externally-defined metrics. These improvements enabled the AoU team to save time on troubleshooting EHR and focus on the development of alternate mechanisms to improve the quality of future EHR submissions. While this framework has proven effective, further efforts to automate and centralize communication channels are needed to deepen the program's efforts while retaining its scalability.


Assuntos
Confiabilidade dos Dados , Registros Eletrônicos de Saúde , Humanos , Fluxo de Trabalho
5.
AMIA Annu Symp Proc ; 2022: 196-205, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35854735

RESUMO

Translation of predictive modeling algorithms into routine clinical care workflows faces challenges in the form of varying data quality-related issues caused by the heterogeneity of electronic health record (EHR) systems. To better understand these issues, we retrospectively assessed and compared the variability of data produced from two different EHR systems. We considered three dimensions of data quality in the context of EHR-based predictive modeling for three distinct translational stages: model development (data completeness), model deployment (data variability), and model implementation (data timeliness). The case study was conducted based on predicting post-surgical complications using both structured and unstructured data. Our study discovered a consistent level of data completeness, a high syntactic, and moderate-high semantic variability across two EHR systems, for which the quality of data is context-specific and closely related to the documentation workflow and the functionality of individual EHR systems.


Assuntos
Confiabilidade dos Dados , Registros Eletrônicos de Saúde , Documentação/métodos , Humanos , Estudos Retrospectivos , Fluxo de Trabalho
7.
Health Informatics J ; 28(3): 14604582221112853, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35793497

RESUMO

Facility based retrospective study was conducted in three regions in southern Ethiopia to assess quality of medical records. A total of 2,145 medical records were reviewed from 73 public health facilities. Minimum standards of medical records were considered to assess completeness and legibility of records. The completeness of medical records were judged systematically according to national HMIS formats. From total of 2,145 medical cards reviewed, only 394 (18.4%) records had all complete and readable data. Gaps observed include 29.0% missed at least one of identification data, 14.3% lack chief compliant, 20.1% lack diagnosis, 12.5% lack medication and 60.3% records had no date and/or signature. Moreover, 9.5% cards had at least one non-readable component. Records at health centers were 56.8% less likely to be quality record as compared to records in hospitals. Even though completeness of every single record is must, only less than one fifth of records met quality of national medical record standard. Ministry of health should consider rules and regulation to maintain data quality and switching to electronic record, and finally progress in data quality should be monitored routinely.


Assuntos
Confiabilidade dos Dados , Registros Médicos , Etiópia , Instalações de Saúde , Humanos , Estudos Retrospectivos
8.
Stud Health Technol Inform ; 295: 398-401, 2022 Jun 29.
Artigo em Inglês | MEDLINE | ID: mdl-35773895

RESUMO

Many decision support methods and systems in pharmacovigilance are built without explicitly addressing specific challenges that jeopardize their eventual success. We describe two sets of challenges and appropriate strategies to address them. The first are data-related challenges, which include using extensive multi-source data of poor quality, incomplete information integration, and inefficient data visualization. The second are user-related challenges, which encompass users' overall expectations and their engagement in developing automated solutions. Pharmacovigilance decision support systems will need to rely on advanced methods, such as natural language processing and validated mathematical models, to resolve data-related issues and provide properly contextualized data. However, sophisticated approaches will not provide a complete solution if end-users do not actively participate in their development, which will ensure tools that efficiently complement existing processes without creating unnecessary resistance. Our group has already tackled these issues and applied the proposed strategies in multiple projects.


Assuntos
Sistemas de Apoio a Decisões Clínicas/normas , Sistemas de Apoio a Decisões Administrativas/normas , Processamento de Linguagem Natural , Farmacovigilância , Confiabilidade dos Dados , Interface Usuário-Computador
9.
Public Health Rep ; 137(1_suppl): 38S-45S, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35775912

RESUMO

Public policy may be strongly influenced by the language used in the media to discuss issues. This language can create a policy image or policy representation that frames the issue as being either deserving or undeserving of policy aid. This policy representation, in turn, may influence the direction of public policies proposed to address the issue. This article presents the development of a codebook for systematically examining the language used in the media to create these policy representations. Framing theory and a qualitative content analysis approach were used to develop the codebook, using a 4-part taxonomy: problem definition, causal interpretation, moral evaluation, and policy recommendation. The issue of juveniles involved in commercial sexual activity in Hawai'i was used as a case study to guide creation of the codebook. Pilot study data were drawn from Hawai'i's local newspapers and from testimony submitted to the Hawai'i State Legislature during 1985-2016. A set of coding schemes built on the 4-part taxonomy was based on the dichotomous attitude of juvenile criminality and juvenile exploitation. Pilot data indicated that juveniles are increasingly being represented as victims of sexual exploitation (newspaper, 45%; testimony, 90%), and the presence of thematic elements in the media strongly correlated with this overall shift. A key lesson learned was the ability of the codebook to capture episodic and thematic elements, which may have strong implications for those concerned with populations that are exploited, politically marginalized, and in need of policy aid. Another key lesson learned was the strength of the codebook to collect quantitative and qualitative data that may lie outside carefully constructed dichotomous frames (eg, a policy representation of juveniles as survivors) and the media's prevailing narratives (eg, the experience of sexual minority juveniles).


Assuntos
Política Pública , Comportamento Sexual , Confiabilidade dos Dados , Hawaii , Humanos , Projetos Piloto
10.
BMC Med Inform Decis Mak ; 22(1): 154, 2022 06 15.
Artigo em Inglês | MEDLINE | ID: mdl-35705966

RESUMO

BACKGROUND: Poor quality routine data contributes to poor decision-making, inefficient resource allocation, loss of confidence in the health system, and may threaten the validity of impact evaluations. For several reasons in most developing countries, the routine health information systems in those countries are described as ineffective. Hence, the aim of this study is to determine the quality of data and associated factors in the routine health management information system in health centers of Shashogo district, Hadiya Zone. METHODS: A facility-based cross-sectional study was conducted from June 1, 2021, to July 1, 2021, and 300 participants were involved in the study through simple random sampling. The data was collected with a self-administered questionnaire by trained data collectors. After checking its completeness, the data was entered into EPI data version 3.1 and exported to SPSS version 25 for statistical analysis. Finally, variables with p < 0.05 during multivariable analysis were considered significant variables. RESULT: A total of 300(100%) participant were included in the interview and HMIS data quality was 83% in Shashogo district health centers. The data quality in terms of accuracy, completeness, and timeliness was 79%, 86%, and 84%, respectively. Conducting supportive supervision [AOR 3.5 (1.4, 8.9)], checking accuracy [AOR 1.3 (1.5, 3.5)], filling registrations [AOR 2.7 (1.44, 7.7)], and confidence level [AOR 1.9 (1.55, 3.35)] were all rated positively found to be factors associated with data quality. CONCLUSION: The overall level of data quality in Shashogo district health centers was found to be below the national expectation level. All dimensions of data quality in the district were below 90% in data accuracy, content completeness, and timeliness of data. Conducting supportive supervision, checking accuracy, filling registrations and confidence level were found to be factors associated with data quality. Hence, all stakeholders should give all necessary support to improve data quality in routine health information systems to truly attain the goal of providing good quality data for the decision-making process by considering the identified factors.


Assuntos
Sistemas de Informação em Saúde , Sistemas de Informação Administrativa , Estudos Transversais , Confiabilidade dos Dados , Etiópia , Humanos
11.
Stud Health Technol Inform ; 290: 130-134, 2022 Jun 06.
Artigo em Inglês | MEDLINE | ID: mdl-35672985

RESUMO

Automated identification of eligible patients for clinical trials is an evident secondary use for electronic health records (EHR) data accumulated during routine care. This task requires relevant data elements to be both available in the EHR and in a structured form. This work analyzes these data quality dimensions of EHR data elements corresponding to a selection of frequent eligibility criteria over a total of 436 patient records at 10 university hospitals within the MIRACUM consortium. Data elements from demographics, diagnosis and laboratory findings are typically structured with a completeness of 73 % to 88 % while medication as well as procedures are rather untructured with a completeness of only 44 %. The results can be used to derive suggestions for data quality improvement measures with respect to patient recruitment as well as to serve as a baseline to quantify future developments.


Assuntos
Confiabilidade dos Dados , Registros Eletrônicos de Saúde , Ensaios Clínicos como Assunto , Humanos , Seleção de Pacientes
12.
Soc Sci Med ; 305: 115064, 2022 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-35653892

RESUMO

Growing evidence suggests that community-based interventions in low- and middle-income countries (LMICs) can effectively address harmful social norms that promote or sustain gender inequality and drive violence against women (VAW). However, understanding what actions communities are already taking to address harmful social norms and prevent VAW is an essential first step for intervention development. Towards this goal, drawing on collective action theory, we conducted a realist analysis of secondary qualitative data collected with communities in India, Afghanistan, Peru and Rwanda. We coded interview and focus-group data from 232 participants to identify the contexts, mechanisms and outcomes (CMO) relevant for community action. We synthesized CMO configurations from each dataset into a conceptual framework composed of three middle-range theories of mechanisms driving community action to prevent VAW in LMICs. Our results highlight the importance of dedicated spaces for discussing VAW, VAW leaders as positive role models, and community perceptions of VAW as a problem worthy of intervention. In Rwanda and Peru, there was strong evidence to support the operation of these mechanisms. Contextual factors, including national and local policy and programmes targeting VAW, activated mechanisms that led to community action. In India and Afghanistan, evidence for the presence of these mechanisms was weaker, with social norms about women's position and violence being a private family matter preventing communities from addressing violence. Despite contextual differences, our data demonstrated communities in all four settings were somewhere along a pathway of change towards VAW prevention. This supports the need to build future prevention interventions on pre-existing mechanisms that trigger community action, rather than implementing existing interventions without local adaptation. Our conceptual framework serves as a tool for assessing these mechanisms of community action as part of intervention development research, centring community knowledge and fostering local ownership for more relevant and sustainable VAW prevention interventions.


Assuntos
Países em Desenvolvimento , Violência , Confiabilidade dos Dados , Feminino , Grupos Focais , Humanos , Pobreza , Violência/prevenção & controle
13.
Rev. Hosp. Ital. B. Aires (2004) ; 42(2): 71-76, jun. 2022. tab
Artigo em Espanhol | LILACS, BINACIS, UNISALUD | ID: biblio-1378656

RESUMO

Introducción: la información sobre las causas de muerte es de gran importancia tanto para los países como para las instituciones sanitarias, en la medida en que contribuye a la evaluación y el seguimiento del estado de salud de la población y a la planificación de intervenciones sanitarias. El objetivo del estudio fue evaluar la proporción de causas de muerte mal definidas e imprecisas y su relación con el día de la semana y período lectivo de médicos residentes en el Hospital Italiano de Buenos Aires (HIBA) durante 2020. Métodos: se realizó un estudio analítico de corte transversal a partir de certificados médicos de defunción de pacientes fallecidos en el ámbito intrahospitalario, evaluando las causas de muerte mal definidas (términos médicos que no aportan información desde el punto de vista clínico y epidemiológico) y las imprecisas (no resultan lo suficientemente específicas como para identificar entidades nosológicas que permitan establecer acciones de prevención y control). Resultados: se analizaron 1030 certificados de defunción, con una proporción de certificados con causa básica de muerte mal definida del 2,3% (n = 24), mientras que en el 17,4% (n = 180) fue imprecisa. No se hallaron diferencias entre la proporción de causas básicas mal definidas y las imprecisas según el día de la semana o período lectivo. Al extender el análisis a todas las causas (básicas, mediatas e inmediatas), la proporción de causas mal definidas fue del 1,6% (n = 40) y la de imprecisas del 51% (n = 1212). Conclusiones: los resultados definen al HIBA como un centro de mediana calidad estadística en el registro de causas de muerte. Se concluye que es necesario mejorarla, para lo que resulta de interés la creación de un plan de capacitación y entrenamiento de los médicos en el grado y el posgrado. (AU)


Introduction: information on causes of death is of great importance both for countries and for health institutions, as it contributes to the evaluation and monitoring of the health status of the population and to the planning of health interventions. The purpose of this study was to evaluate the proportion of ill-defined and imprecise causes of death and its relationship with the day of the week and academic calendar during 2020 at the Hospital Italiano de Buenos Aires. Methods: a cross-sectional study was carried out from data recorded in the death certificates of patients who died in the intrahospital setting, evaluating ill-defined causes of death (medical terms that do not provide clinical or epidemiological information) and imprecise ones (not specific enough to identify nosological entities susceptible to prevention or control). Results: 1030 death certificates were analyzed. The proportion of certificates with ill-defined underlying causes of death was 2.3% (n=24), while 17.4% (n=180) was imprecise. No significant differences were found between the ill-defined and imprecise underlying causes of death and the day of the week and academic calendar. When extending the analysis to all causes (underlying, intermediate, and immediate) the percentage of ill-defined causes was 1.6% (n=40) and 51% (n=1212) was imprecise. Conclusions: results define our hospital as of medium statistical quality on medical death certification. It is concluded that it is necessary to improve the quality of the registry, for which the creation of a training plan for undergraduate and graduate physicians is of interest. (AU)


Assuntos
Humanos , Causas de Morte/tendências , Mortalidade Hospitalar/tendências , Argentina , Atestado de Óbito , Estudos Transversais , Confiabilidade dos Dados , Análise de Dados
14.
Stud Health Technol Inform ; 290: 983-984, 2022 Jun 06.
Artigo em Inglês | MEDLINE | ID: mdl-35673167

RESUMO

A generic approach for assessment and continuous monitoring of data quality in ODM-based research data has been developed. The focus is on the two data quality indicators completeness and syntactic correctness. The main idea is to enable the generation of a data quality report without additional programming effort.


Assuntos
Pesquisa Biomédica , Confiabilidade dos Dados , Monitorização Fisiológica
15.
Stud Health Technol Inform ; 290: 987-988, 2022 Jun 06.
Artigo em Inglês | MEDLINE | ID: mdl-35673169

RESUMO

We have developed data quality tool in R language. Our application name is Package-Data-Quality-Assessment (PackDQA)". It developed following five points: Quality dimension approaches identification, design of quality measures, global coefficient design, development of the quality model, test and deployment model. This model test performed on health data in Burkina Faso show 97.69% observations is quality. The current version does not include qualitative data. We will have to improve theme to use all types of data.


Assuntos
Confiabilidade dos Dados , Idioma , Burkina Faso
16.
Am Soc Clin Oncol Educ Book ; 42: 1-17, 2022 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-35658501

RESUMO

Sexual and gender minority (SGM) people, including agender, asexual, bisexual, gay, gender diverse, genderqueer, genderfluid, intersex, lesbian, nonbinary, pansexual, queer, and transgender people, comprise approximately 10% or more of the U.S. population. Thus, most oncologists see SGM patients whether they know it or not. SGM people experience stigma and structural discrimination that lead to cancer disparities. Because of the lack of systematic and comprehensive data collection, data regarding SGM cancer incidence, outcomes, and treatment responses are limited. Collection of data regarding sexual orientation, gender identity, transgender identity and/or experience, anatomy, and serum hormone concentrations in oncology settings would drastically increase collective knowledge about the impact of stigma and biologic markers on cancer outcomes. Increasing the safety of oncology settings for SGM people will require individual, institutional, and systems changes that will likely improve oncologic care for all patients.


Assuntos
Neoplasias , Minorias Sexuais e de Gênero , Confiabilidade dos Dados , Feminino , Identidade de Gênero , Humanos , Masculino , Neoplasias/diagnóstico , Neoplasias/epidemiologia , Neoplasias/terapia , Comportamento Sexual
17.
BMC Public Health ; 22(1): 1266, 2022 06 29.
Artigo em Inglês | MEDLINE | ID: mdl-35768861

RESUMO

BACKGROUND: South Africa's National Health Laboratory Service (NHLS), the only clinical laboratory service in the country's public health sector, is an important resource for monitoring public health programmes. OBJECTIVES: We describe NHLS data quality, particularly patient demographics among infants, and the effect this has on linking multiple test results to a single patient. METHODS: Retrospective descriptive analysis of NHLS data from 1st January 2017-1st September 2020 was performed. A validated probabilistic record-linking algorithm linked multiple results to individual patients in lieu of a unique patient identifier. Paediatric HIV PCR data was used to illustrate the effect on monitoring and evaluating a public health programme. Descriptive statistics including medians, proportions and inter quartile ranges are reported, with Chi-square univariate tests for independence used to determine association between variables. RESULTS: During the period analysed, 485 300 007 tests, 98 217 642 encounters and 35 771 846 patients met criteria for analysis. Overall, 15.80% (n = 15 515 380) of all encounters had a registered national identity (ID) number, 2.11% (n = 2 069 785) were registered without a given name, 63.15% (n = 62 020 107) were registered to women and 32.89% (n = 32 304 329) of all folder numbers were listed as either the patient's date of birth or unknown. For infants tested at < 7 days of age (n = 2 565 329), 0.099% (n = 2 534) had an associated ID number and 48.87% (n = 1 253 620) were registered without a given name. Encounters with a given name were linked to a subsequent encounter 40.78% (n = 14 180 409 of 34 775 617) of the time, significantly more often than the 21.85% (n = 217 660 of 996 229) of encounters registered with a baby-derivative name (p-value < 0.001). CONCLUSION: Unavailability and poor capturing of patient demographics, especially among infants and children, affects the ability to accurately monitor routine health programmes. A unique national patient identifier, other than the national ID number, is urgently required and must be available at birth if South Africa is to accurately monitor programmes such as the Prevention of Mother-to-Child Transmission of HIV.


Assuntos
Infecções por HIV , Transmissão Vertical de Doenças Infecciosas , Criança , Saúde da Criança , Confiabilidade dos Dados , Data Warehousing , Feminino , Infecções por HIV/diagnóstico , Infecções por HIV/epidemiologia , Infecções por HIV/prevenção & controle , Humanos , Lactente , Recém-Nascido , Transmissão Vertical de Doenças Infecciosas/prevenção & controle , Estudos Retrospectivos , África do Sul/epidemiologia
18.
Comput Intell Neurosci ; 2022: 7893792, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35726293

RESUMO

We propose in this paper a fuzzy BP neural network model and DDAE-SVR deep neural network model to analyze multimodal digital teaching, establish a multimodal digital teaching quality data evaluation model based on a fuzzy BP neural network, and optimize the initial weights and thresholds of BP neural network by using adaptive variation genetic algorithm. Since the BP neural network is highly dependent on the initial weights and points, the improved genetic algorithm is used to optimize the initial weights and thresholds of the BP neural network, reduce the time for the BP neural network to find the importance and points that satisfy the training termination conditions, and improve the prediction accuracy and convergence speed of the neural network on the teaching quality evaluation results. The entropy value method, a data-based objectivity evaluation method, is introduced as the guidance mechanism of the BP neural network. The a priori guidance sample is obtained by the entropy method. Then, the adaptive variational genetic algorithm is used to optimize the BP neural network model to learn the a priori sample knowledge and establish the evaluation model, which reduces the subjectivity of the BP neural network learning sample. To better reflect and compare the effects of the two neural network evaluation models, BP and GA-BP, the sample data were continued to be input into the original GA and BSA to obtain the evaluation results and errors; then, the evaluation results of the two evaluation models, BP and GA-BP, were compared with the evaluation results of the two algorithms, GA and BSA. It was found that the GA-BP neural network evaluation model has higher accuracy and can be used for multimodal digital teaching quality evaluation, providing a more feasible solution.


Assuntos
Algoritmos , Redes Neurais de Computação , Confiabilidade dos Dados
19.
Comput Intell Neurosci ; 2022: 6776603, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35755733

RESUMO

In this paper, we use a particle swarm optimization neural network algorithm to analyze the teaching data of physical education faculties and evaluate the quality of teaching in physical education faculties. By studying and analyzing the optimization problem of the weight parameters of convolutional neural network training, this paper designs a hybrid algorithm combining the improved PSO algorithm and the traditional gradient descent in the framework of the BP algorithm by using the gradient information of the loss function and the principle of group cooperative search through PSO algorithm. The hybrid algorithm takes the loss function as the objective function, based on the principle of the PSO algorithm, and optimizes the objective function by combining the gradient information of the loss function of the convolutional neural network. The convergence speed and global search ability of the algorithm are effectively improved while ensuring an acceptable increase in computation. The weight values of the three-level indicators of teacher teaching behavior, student learning behavior, and teaching environment relative to the teaching quality of physical education classroom are 0.106, 0.634, and 0.260, respectively, which shows that the dimension of student learning behavior has the highest weight value in the evaluation of physical education classroom teaching quality, followed by teaching environment and finally teacher teaching behavior. Teachers' teaching ability will affect the effect of teaching methods, and the stronger the teaching ability is, the better the selection and utilization of teaching methods can be optimized.


Assuntos
Algoritmos , Redes Neurais de Computação , Simulação por Computador , Confiabilidade dos Dados , Humanos , Aprendizagem
20.
Sensors (Basel) ; 22(11)2022 Jun 06.
Artigo em Inglês | MEDLINE | ID: mdl-35684922

RESUMO

The Internet of Things (IoT) is prone to malware assaults due to its simple installation and autonomous operating qualities. IoT devices have become the most tempting targets of malware due to well-known vulnerabilities such as weak, guessable, or hard-coded passwords, a lack of secure update procedures, and unsecured network connections. Traditional static IoT malware detection and analysis methods have been shown to be unsatisfactory solutions to understanding IoT malware behavior for mitigation and prevention. Deep learning models have made huge strides in the realm of cybersecurity in recent years, thanks to their tremendous data mining, learning, and expression capabilities, thus easing the burden on malware analysts. In this context, a novel detection and multi-classification vision-based approach for IoT-malware is proposed. This approach makes use of the benefits of deep transfer learning methodology and incorporates the fine-tuning method and various ensembling strategies to increase detection and classification performance without having to develop the training models from scratch. It adopts the fusion of 3 CNNs, ResNet18, MobileNetV2, and DenseNet161, by using the random forest voting strategy. Experiments are carried out using a publicly available dataset, MaleVis, to assess and validate the suggested approach. MaleVis contains 14,226 RGB converted images representing 25 malware classes and one benign class. The obtained findings show that our suggested approach outperforms the existing state-of-the-art solutions in terms of detection and classification performance; it achieves a precision of 98.74%, recall of 98.67%, a specificity of 98.79%, F1-score of 98.70%, MCC of 98.65%, an accuracy of 98.68%, and an average processing time per malware classification of 672 ms.


Assuntos
Internet das Coisas , Segurança Computacional , Confiabilidade dos Dados , Mineração de Dados , Redes Neurais de Computação
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...