Multiple Data Research Articles

Survey Paper on A Machine Learning Approach for Multiple Disease Prediction

Machine learning techniques have revolutionized the field of healthcare by enabling accurate and timely disease prediction. The ability to predict multiple diseases simultaneously can significantly improve early diagnosis and treatment, leading to better patient outcomes and reduced healthcare costs. This research paper explores the application of machine learning algorithms in predicting multiple diseases, focusing on their benefits, challenges, and future directions. We present an overview of various machine learning models and data sources commonly used for disease prediction. Additionally, we discuss the importance of feature selection, model evaluation, and the integration of multiple data modalities for enhanced disease prediction. The research findings highlight the potential of machine learning in multi- disease prediction and its potential impact on public health. Once more, I am applying machine learning model to identify that a person is affected with few disease or not. This training model takes a sample data and train itself for predicting disease. Key Words: Disease Prediction, Na ̈ıve Bayesian Networks, Random Forest, Decision Tree, Feature , Selection KNN.

A new circular neural grey model and its application to CO2 emissions in China

The accurate prediction of China's CO2 emissions provides a reference and early warning for the implementation of the government's environmental strategy and has far-reaching significance for the world's environmental protection. The carbon emission system is a nonlinear dynamical system influenced by multiple factors with multiple data features. This paper establishes a novel grey differential dynamic multivariate prediction model with recurrent neural network. It uses the grey differential dynamic multivariate prediction model to describe the dynamic characteristics of the nonlinear system. And it uses recurrent neural network to extract data features. The new model is used to compensate for the shortcomings of the grey prediction model that use the least squares method to solve the model parameters affecting the accuracy of the model. The numerical solution of the whitening equations of the new model visualizes the hidden layer state function of the recurrent neural network. The optimal parameters of the new model are obtained through repeated training to improve the prediction accuracy of the model. Finally, the new model is applied to the prediction of China's CO2 emissions to verify the validity of the new model from four different perspectives. The results show that the simulation and prediction errors of the new model for data of different lengths are less than 5%. The average simulation error in the optimal scheme is 3.01%, and the average prediction error is 0.78%. The results of the new model are better than the results of the other models. This indicates that the new model has better prediction results. Applying the scenario in forecasting the amount of carbon dioxide in China from 2020 to 2026 yields a forecast that matches the actual trend, further illustrating the validity and feasibility of the model. Finally, the forecast results are analysed, and relevant policy recommendations are provided.

Web Page Ranking Based on Text Content and Link Information Using Data Mining Techniques

Thanks to the rapid expansion of the Internet, anyone can now access a vast array of information online. However, as the volume of web content continues to grow exponentially, search engines face challenges in delivering relevant results. Early search engines primarily relied on the words or phrases found within web pages to index and rank them. While this approach had its merits, it often resulted in irrelevant or inaccurate results. To address this issue, more advanced search engines began incorporating the hyperlink structures of web pages to help determine their relevance. While this method improved retrieval accuracy to some extent, it still had limitations, as it did not consider the actual content of web pages. The objective of the work is to enhance Web Information Retrieval methods by leveraging three key components: text content analysis, link analysis, and log file analysis. By integrating insights from these multiple data sources, the goal is to achieve a more accurate and effective ranking of relevant web pages in the retrieved document set, ultimately enhancing the user experience and delivering more precise search results the proposed system was tested with both multi-word and single-word queries, and the results were evaluated using metrics such as relative recall, precision, and F-measure. When compared to Google’s PageRank algorithm, the proposed system demonstrated superior performance, achieving an 81% mean average precision, 56% average relative recall, and a 66% F-measure.

Feature analysis of precipitation-induced subgrade defects on a high-speed rail ballasted track using multiple track inspection data: A case study

Heavy rainfall has posed a great challenge to the service performance of high-speed rail (HSR) substructure, resulting in a reduction in the ride quality and safety of high-speed trains. To carry out proper repair work for the substructure, it is imperative to realize efficient identification of precipitation-induced subgrade defects. To this end, this paper aims to extract the features of typical precipitation-induced subgrade defects from the multiple track inspection data to provide a basis for defect identification. Firstly, the geotechnical site investigation including Ground Penetrating Radar (GPR) detection, moisture content test, and dynamic cone penetration (DCP) test of a typical defective spot is performed to determine the condition of the subgrade after heavy rainfall; then, the analysis methods of track inspection data are introduced; finally, the track geometry data and carbody acceleration data of four typical defective sections are analyzed, and the time-domain, frequency-domain and discrete wavelet transform (DWT)-based features which are highly correlated with the precipitation-induced subgrade defects are extracted. The results show that the feature indexes extracted from track surface irregularity and carbody vertical acceleration increase significantly after heavy rainfall; the long wavelength components (8 m and above) of both track irregularity and carbody vibration are more sensitive to the subgrade defects, which is reflected by the sharp increase of the DWT-based features at some levels corresponding to long wavelength ranges. The results of defect feature extraction based on the track inspection data agree well with the geotechnical site investigation results, which demonstrate the feasibility of utilizing multiple track inspection data to identify the typical precipitation-induced subgrade defects.

De novo prediction of RNA 3D structures with deep generative models.

We present a Deep Learning approach to predict 3D folding structures of RNAs from their nucleic acid sequence. Our approach combines an autoregressive Deep Generative Model, Monte Carlo Tree Search, and a score model to find and rank the most likely folding structures for a given RNA sequence. We show that RNA de novo structure prediction by deep learning is possible at atom resolution, despite the low number of experimentally measured structures that can be used for training. We confirm the predictive power of our approach by achieving competitive results in a retrospective evaluation of the RNA-Puzzles prediction challenges, without using structural contact information from multiple sequence alignments or additional data from chemical probing experiments. Blind predictions for recent RNA-Puzzle challenges under the name "Dfold" further support the competitive performance of our approach.

The effect of human resource development and leadership on employee performance with organizational commitment

<p>Employee development greatly affects the development of the organization. Professionally developed employees can bring various benefits to the organization. This study aims to analyze the influence of human resource development and leadership on employee performance with organizational commitment as a moderation variable in Batamindo Industrial Park companies. Human resource development aims to increase employee knowledge in terms of knowledge and practice skills through education, training, non-training and learning tasks. Furthermore, employee performance is the quality of work results, quantity of work, attendance and teamwork ability. This study uses a qualitative approach with a correlational associative research method by distributing questionnaires to employees June-July 2023 using <em>a google form</em>. The research sample was taken by purposive sampling involving 100 respondents. Data analysis was carried out using multiple regression analysis and data was processed using Smart PLS 3. The results of this study show that leadership variables and organizational commitment have a significant effect on employee performance. Human resource development does not have a significant effect on employee performance, this is due to HR development that is not implemented properly or without a mature plan so that it does not have a significant impact. Poor execution and lack of support from management. Organizational commitment is proven to be able to strengthen the influence of leadership and human resource development on employee performance.</p>

Unravelling spatiotemporal patterns of solar photovoltaic plants development in China in the 21st century

Solar energy, as an environmentally sustainable power source, is gaining increasing popularity worldwide, driving a surge in the number of solar photovoltaic (PV) plants. China, which has a prominent role in this domain, requires continuous updates to its PV plant data for spatiotemporal analyses. However, there remains an absence of a comprehensive and timely dataset of PV plants across China, leaving PV installation dates and other crucial attributes for comprehensive analyses underexplored. This study leverages Sentinel-2 data as a primary source to propose an optimized deep learning approach for PV plant extraction in China. Statistical analyses of PV plant attributes, including its installation date, size, site slope, and site land cover, were implemented from multiple data sources. Comprehensive analyses were conducted to unravel their spatiotemporal development patterns in the 21st century. The results indicate that as of 2023, China boasts 4347 PV plants, collectively spanning 4146 km2, which are predominantly concentrated in Northwest and North China. 2016 and 2017 marked substantial growth in China’s PV plants, while other years exhibited stability. These plants exhibit the distinct spatial characteristics of installing smaller PV plants on flat terrain covered by vegetation or barren land. Over time, a notable trend in the installation of China’s PV plants has been the increasing preference for establishing larger ones in smooth terrain, with a focus on preventing damage to natural resources. The results reveal China’s optimization of PV plant site selection and construction strategies, aligning with global environmental goals and sustainable energy practices.

Dimension reduction and outlier detection of 3-D shapes derived from multi-organ CT images

BackgroundUnsupervised clustering and outlier detection are important in medical research to understand the distributional composition of a collective of patients. A number of clustering methods exist, also for high-dimensional data after dimension reduction. Clustering and outlier detection may, however, become less robust or contradictory if multiple high-dimensional data sets per patient exist. Such a scenario is given when the focus is on 3-D data of multiple organs per patient, and a high-dimensional feature matrix per organ is extracted.MethodsWe use principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE) and multiple co-inertia analysis (MCIA) combined with bagplots to study the distribution of multi-organ 3-D data taken by computed tomography scans. After point-set registration of multiple organs from two public data sets, multiple hundred shape features are extracted per organ. While PCA and t-SNE can only be applied to each organ individually, MCIA can project the data of all organs into the same low-dimensional space.ResultsMCIA is the only approach, here, with which data of all organs can be projected into the same low-dimensional space. We studied how frequently (i.e., by how many organs) a patient was classified to belong to the inner or outer 50% of the population, or as an outlier. Outliers could only be detected with MCIA and PCA. MCIA and t-SNE were more robust in judging the distributional location of a patient in contrast to PCA.ConclusionsMCIA is more appropriate and robust in judging the distributional location of a patient in the case of multiple high-dimensional data sets per patient. It is still recommendable to apply PCA or t-SNE in parallel to MCIA to study the location of individual organs.

Regional Disparities in Safe and Clean Environments in Uzbekistan: Analysis of 2021–2022 Uzbekistan Multiple Indicator Cluster Survey Data

Background: Water, sanitation, and hygiene (WASH) services and clean fuels are representative factors of a clean and safe residential environment. Uzbekistan faces environmental issues and ranks low among countries on the Environmental Performance Index. This study aimed to identify regional disparities and wealth inequalities in WASH services and clean fuels in Uzbekistan. Methods: We employed raw data from the 2021–2022 Uzbekistan Multiple Indicator Cluster Survey (MICS) and the WASH and clean fuels coverage were analyzed. For each of the variables with the lowest coverage within WASH services and clean fuels variables, we evaluated the disparities between urban and rural areas and calculated the concentration index (CI). Results: Among WASH services and clean fuels, basic handwashing and clean fuels for space heating demonstrated the lowest coverage. In most regions, urban areas had higher coverage of basic handwashing and clean fuels for space heating compared to rural areas. The CI of clean fuels for space heating was 0.2141 or higher in five areas. The CI was notably high in areas with low coverage of WASH services and clean fuel for space heating. Conclusions: Basic handwashing and clean fuels for space heating showed varied regional coverage patterns and wealth-related inequalities. The results of this study can provide evidence for policy formulation, particularly in addressing disparities.

Deep learning for drug‐drug interaction prediction: A comprehensive review

AbstractThe prediction of drug‐drug interactions (DDIs) is a crucial task for drug safety research, and identifying potential DDIs helps us to explore the mechanism behind combinatorial therapy. Traditional wet chemical experiments for DDI are cumbersome and time‐consuming, and are too small in scale, limiting the efficiency of DDI predictions. Therefore, it is particularly crucial to develop improved computational methods for detecting drug interactions. With the development of deep learning, several computational models based on deep learning have been proposed for DDI prediction. In this review, we summarized the high‐quality DDI prediction methods based on deep learning in recent years, and divided them into four categories: neural network‐based methods, graph neural network‐based methods, knowledge graph‐based methods, and multimodal‐based methods. Furthermore, we discuss the challenges of existing methods and future potential perspectives. This review reveals that deep learning can significantly improve DDI prediction performance compared to traditional machine learning. Deep learning models can scale to large‐scale datasets and accept multiple data types as input, thus making DDI predictions more efficient and accurate.

Multiple Factors Drive the Development of Scientific Thinking in Urban Primary School Students of China: FsQCA Analysis Based on the Ecological Systems Theory

With the introduction and implementation of core literacy, scientific thinking (ST) has become an essential goal and key dimension of science teaching. At present, there is no agreement on how to cultivate students’ ST. This study took 238 sixth grade students from a public primary school in urban China as research sample, built a theoretical model of scientific thinking development based on the theory of the Bronfenbrenner’ ecological systems theory, and used multiple data to explore and analyze the impact path of ST development of primary school students using the fuzzy sets of qualitative comparative analysis method (fsQCA). The development of urban primary school students’ ST is the result of multiple factors at the level of individual drive, family environment, school teaching, and social resources. The result of data analysis showed that the influence path of ST development of urban primary school students driven by multiple factors includes three paths: parent participation leading, scientific practice leading, and home-school-community integration. We have interpreted the influence mechanism of each path in detail and put forward the enlightenment for science education policy and practice.

Individual- and community-level factors associated with the presence of adequate iodized salt in households in Bangladesh: a multilevel modelling approach.

The aim of this study is to estimate the factors at both the individual and community levels related to the adequacy of iodized salt in households in Bangladesh. For this study we utilized the 2019 Multiple Indicator Cluster Survey data. A total of 61242 households were chosen as samples from Bangladesh. In our study of socio-economic disparities, we applied a concentration indexing method. To identify the factors associated with the adequacy of iodine in salt at both the individual and community levels, we employed multilevel logistic regression. Aside from the multilevel regression used in the study, we also applied spatial analysis. The results indicated that the prevalence of iodine adequacy in household salt was found to be 57.8% (95% confidence interval 57.4 to 58.2). Rural areas have a higher concentration of iodine than urban areas. According to the multilevel model, younger women (adjusted odds ratio [aOR] 0.70), Muslim women (aOR 0.89), illiterate women (aOR 0.80) and those from poor households (aOR 0.33) were found to be less likely to consume iodine in concentrated salt compared with their counterparts. Disabled women and those with low media exposure have a lower likelihood of iodine adequacy in salt compared to their reference group. Furthermore, households in urban areas exhibited higher odds of having iodine adequacy in salt compared with households in rural areas. Barisal, Chattogram, Dhaka, Khulna, Mymensingh, Rajshahi and Rangpur Divisions have lower iodine adequacy in salt compared with Sylhet Division. The findings reveal that religion, physical disability and exposure to media exert an equal influence on the presence of iodized salt intake. Moreover, women's age, wealth status, education level and the educational background of the household head positively contribute to the adequacy of iodine in household salt. In light of these results, policymakers are advised to prioritize efforts aimed at enhancing iodine concentration, with a particular focus on mass media advertising, especially in rural areas (excluding Sylhet Division).

GPS-free roll and pitch estimation through pressure altitude aided inertial navigation system for a jet aircraft

This paper presents a novel approach for estimating roll and pitch angles of an aircraft by regulating the dead-reckoning drift using pressure altitude measurements. The proposed algorithm uses measurements from rate gyroscopes, pressure altitude, and an air data system to estimate the roll and pitch angles of an aircraft. This unique combination of sensor data offers a new alternative to traditional navigation approaches relying on accelerometers and satellite systems to estimate the aircraft attitude. Multiple flight data sets from a high-speed crewed US Navy T-38 jet are used to validate the proposed approach. Comparable levels of attitude estimation accuracy are reported thus demonstrating that the proposed algorithm is a viable alternative for attitude estimation purposes. Therefore, this approach can be used to improve the robustness and accuracy of attitude estimation algorithms in scenarios where GPS coverage is denied, unreliable, spoofed and/or jammed.

Barriers to accessibility of medicines for hyperlipidemia in low- and middle-income countries.

Despite the high burden of hyperlipidemia and the effectiveness of treatment, evidence suggests that the accessibility of hyperlipidemia medicines can be low in many low- and middle-income countries (LMICs). The aim of this study was to identify common barriers to the accessibility of medicines for hyperlipidemia in LMICs. A multimethod analysis and multiple data sources were used to assess the accessibility and barriers of medicines for hyperlipidemia in selected LMICs. The overall median availability of statins for hyperlipidemia in public facilities was 0% and 5.4%, for originators and generics, respectively. In private facilities, median availability was 13.3% and 35.9%, for originators and generics, respectively. Statin availability was lowest in Africa and South-East Asia. Private facilities generally had higher availability than public facilities. Statins are less affordable in lower-income countries, costing around 6 days' wages per month. Originator statins are less affordable than generics in countries of all income-levels. The median cost for statin medications per month ranges from a low of $1 in Kenya to a high of $62 in Mexico, with most countries having a median monthly cost between $3.6 and $17.0. The key informant interviews suggested that accessibility to hyperlipidemia medicines in LMICs faces barriers in multiple dimensions of health systems. The availability and affordability of statins are generally low in LMICs. Several steps could be implemented to improve the accessibility of hyperlipidemia medicines, including private sector engagement, physician education, investment in technology, and enhancement of health systems.

Decision Support Systems in Forestry and Tree-Planting Practices and the Prioritization of Ecosystem Services: A Review

In this study, tree-selection/plantation decision support systems (DSSs) were reviewed and evaluated against essential objectives in the available literature. We verified whether existing DSSs leverage multiple data sources and available online resources such as web interfaces. We compared the existing DSSs, and in this study mainly focused on five main objectives that DSSs can consider in tree selection, including (a) climate resilience, (b) infrastructure/space optimization, (c) agroforestry, (d) ecosystem services, and (e) urban sustainability. The climate resilience of tree species and urban sustainability are relatively rarely taken into account in existing systems, which can be integrated holistically in future DSS tools. Based on this review, deep neural networks (DNNs) are recommended to achieve trade-offs between complex objectives such as maximizing ecosystem services, the climate resilience of tree species, agroforestry conservation, and other benefits.

Correlation enhanced distribution adaptation for prediction of fall risk

With technological advancements in diagnostic imaging, smart sensing, and wearables, a multitude of heterogeneous sources or modalities are available to proactively monitor the health of the elderly. Due to the increasing risks of falls among older adults, an early diagnosis tool is crucial to prevent future falls. However, during the early stage of diagnosis, there is often limited or no labeled data (expert-confirmed diagnostic information) available in the target domain (new cohort) to determine the proper treatment for older adults. Instead, there are multiple related but non-identical domain data with labels from the existing cohort or different institutions. Integrating different data sources with labeled and unlabeled samples to predict a patient's condition poses a significant challenge. Traditional machine learning models assume that data for new patients follow a similar distribution. If the data does not satisfy this assumption, the trained models do not achieve the expected accuracy, leading to potential misdiagnosing risks. To address this issue, we utilize domain adaptation (DA) techniques, which employ labeled data from one or more related source domains. These DA techniques promise to tackle discrepancies in multiple data sources and achieve a robust diagnosis for new patients. In our research, we have developed an unsupervised DA model to align two domains by creating a domain-invariant feature representation. Subsequently, we have built a robust fall-risk prediction model based on these new feature representations. The results from simulation studies and real-world applications demonstrate that our proposed approach outperforms existing models.

The effect of service quality and brand image on customer loyalty with consumer satisfaction as a mediation variable in shopee e commerce

This study aims to analyze the effect of service quality and brand image on customer loyalty on the Shopee e-commerce platform, by considering consumer satisfaction as a moderating variable. This study uses a survey method using a questionnaire distributed to active Shopee customers who have made transactions carried out in January-June 2023. The research sample was taken by purposive sampling involving 250 respondents. Data analysis was carried out using multiple regression analysis and data was processed using Smart PLS 3. The results of this study show that service quality has a significant positive effect on Shopee customer loyalty. In addition, brand image also has a significant positive influence on customer loyalty. This finding shows that the quality of service and Shopee's brand image are important factors in building customer loyalty. Furthermore, consumer satisfaction has also proven to be a significant moderating variable in the relationship between service quality brand image, and customer loyalty. Service quality has a positive and significant influence on customer loyalty through customer satisfaction. Customer satisfaction is a key factor in building customer loyalty, and good service quality can increase the level of customer satisfaction. When customers receive good services, such as prompt responses, effective assistance, and timely delivery, they will have a positive experience.

Retraction Note: Graphical representation of network meta-analysis: an iconographic support to the complexity of multiple data comparisons.

Retraction Note: Graphical representation of network meta-analysis: an iconographic support to the complexity of multiple data comparisons.

Epidemiology and Outcomes of Non–Small Cell Lung Cancer in South Korea

Valuable evidence regarding clinical characteristics, treatments, and outcomes for non-small cell lung cancer (NSCLC) is limited to individual hospital databases or national-level registries. The common data and federated analysis framework developed through the Extensible Platform for Observational Research in Lung Cancer (EXPLORE-LC) initiative allows for research across multiple high-quality data sources, which may provide a deeper understanding of the NSCLC landscape and identification of unmet needs of subpopulations. To describe clinical characteristics, initial treatment patterns, subsequent treatment, and overall survival (OS) of patients with NSCLC in South Korea. This multicenter cohort study included patients aged 18 years and older who were diagnosed with NSCLC between 2014 and 2019 and followed up until March 2020 at 3 tertiary hospitals in South Korea. Clinical data were collected using a common data model and clinical data warehouse. Patients who had an initial diagnosis of nonsquamous (NSQ) or squamous (SQ) NSCLC and who had received at least 1 treatment for NSCLC were included in the study. Data were analyzed from June through November 2022. The primary outcome was clinical OS for patients with NSCLC. Secondary outcomes were clinical characteristics and treatment patterns subsequent to the diagnosis of NSCLC. Among 22 101 patients with NSCLC who received anticancer treatment analyzed in this study, 17 350 patients (78.5%) had NSQ and 4751 patients (21.5%) had SQ NSCLC. Clinical characteristics and outcomes and treatment patterns were assessed for 13 084 patients with NSQ cancer who had known EGFR and ALK status (75.4%; mean [SD] 62.2 [10.5] years; 6552 males [50.1%]) and all 4751 patients with SQ cancer (mean [SD] age, 67.1 [8.6] years; 4427 males [93.2%]). More than half of patients with NSQ cancer were never smokers (7399 patients [56.6%]). Patients with SQ cancer were mostly males and former or current smokers (4235 patients [89.1%]) and were diagnosed at a later clinical stage than patients with NSQ cancer (eg, stage I: 1165 patients [24.5%] vs 5388 patients [41.2%]). Patients with EGFR-positive and ALK-positive NSQ cancer diagnosed between 2017 and 2019 had better median OS than similar patients diagnosed between 2014 and 2016 (EGFR-positive: not reached [95% CI, 35.9 months to not reached] vs 28.4 months [95% CI, 25.8 to 30.0 months]; P < .001; ALK-positive: not reached [95% CI, not reached] vs 49.5 months [95% CI, 35.1 months to not reached]; P < .001). No significant difference was observed in OS from first-line treatment for patients with SQ cancer. This study, which pooled medical data from multiple clinical data warehouses to produce a large study cohort, may provide meaningful insights into the clinical practice of NSCLC and underscores the value of a common data model approach. The analyzable dataset may hold great promise for future comprehensive identification of subpopulations and unmet needs.

Hydraulic model for flood inundation in Diyala River Basin using HEC-RAS, PMP, and neural network

Abstract The Diyala River Basin in Iraq is vital for water supply to residential, agricultural, and the Tigris River (with approximately 4.5 billion cubic meters annually), but it faces frequent floods and droughts due to reliance on rainfall. This study aims to address these issues by simulating flood inundation using the hydrological engineering centre-river analysis system model and predicting high-intensity rainfall with artificial neural networks. ArcGIS and remote sensing tools aid model development with data from official sources and organizations such as national aeronautics and space administration and food and agriculture organization. The hydraulic model is calibrated using satellite imagery to depict a 2019 flood, and artificial intelligence predicts the precipitation patterns for the next 50 years based on historical data from 1981 to 2021. One of the challenges and difficulties encountered in the study is the scarcity of available data, as well as the absence of scientific research pertaining to the region regarding hydraulic modeling. The study identifies flood risks in March and April every year, notably for the Hemrin Dam, which may exceed permissible water levels (reach a level over 110 m where the Hemrin Crest level is 109.5 m). To mitigate this, an artificial canal is proposed to divert water annually, protecting the dam and downstream areas without disrupting operations. The diverted water could also augment the Tigris River in Kut Governorate during summer. The study demonstrates the value of integrating multiple modeling techniques and data sources for accurate hydraulic predictions. It offers insights for decision-makers in flood management and planning. This study contributes to efficient flood management strategies by adopting a multidisciplinary approach.