Search results

The purpose of the paper is to study multiple viewpoints which are required to access the more informative similarity features among the tweets documents, which is useful for achieving the robust tweets data clustering results.

Let “N” be the number of tweets documents for the topics extraction. Unwanted texts, punctuations and other symbols are removed, tokenization and stemming operations are performed in the initial tweets pre-processing step. Bag-of-features are determined for the tweets; later tweets are modelled with the obtained bag-of-features during the process of topics extraction. Approximation of topics features are extracted for every tweet document. These set of topics features of N documents are treated as multi-viewpoints. The key idea of the proposed work is to use multi-viewpoints in the similarity features computation. The following figure illustrates multi-viewpoints based cosine similarity computation of the five tweets documents (here N = 5) and corresponding documents are defined in projected space with five viewpoints, say, v₁,v₂, v₃, v₄, and v₅. For example, similarity features between two documents (viewpoints v₁, and v₂) are computed concerning the other three multi-viewpoints (v₃, v₄, and v₅), unlike a single viewpoint in traditional cosine metric.

Healthcare problems with tweets data. Topic models play a crucial role in the classification of health-related tweets with finding topics (or health clusters) instead of finding term frequency and inverse document frequency (TF–IDF) for unlabelled tweets.

Topic models play a crucial role in the classification of health-related tweets with finding topics (or health clusters) instead of finding TF-IDF for unlabelled tweets.

The aim of this study is to propose a deep neural network (DNN) method that uses side information to improve clustering results for big datasets; also, the authors show that applying this information improves the performance of clustering and also increase the speed of the network training convergence.

In data mining, semisupervised learning is an interesting approach because good performance can be achieved with a small subset of labeled data; one reason is that the data labeling is expensive, and semisupervised learning does not need all labels. One type of semisupervised learning is constrained clustering; this type of learning does not use class labels for clustering. Instead, it uses information of some pairs of instances (side information), and these instances maybe are in the same cluster (must-link [ML]) or in different clusters (cannot-link [CL]). Constrained clustering was studied extensively; however, little works have focused on constrained clustering for big datasets. In this paper, the authors have presented a constrained clustering for big datasets, and the method uses a DNN. The authors inject the constraints (ML and CL) to this DNN to promote the clustering performance and call it constrained deep embedded clustering (CDEC). In this manner, an autoencoder was implemented to elicit informative low dimensional features in the latent space and then retrain the encoder network using a proposed Kullback–Leibler divergence objective function, which captures the constraints in order to cluster the projected samples. The proposed CDEC has been compared with the adversarial autoencoder, constrained 1-spectral clustering and autoencoder + k-means was applied to the known MNIST, Reuters-10k and USPS datasets, and their performance were assessed in terms of clustering accuracy. Empirical results confirmed the statistical superiority of CDEC in terms of clustering accuracy to the counterparts.

First of all, this is the first DNN-constrained clustering that uses side information to improve the performance of clustering without using labels in big datasets with high dimension. Second, the author defined a formula to inject side information to the DNN. Third, the proposed method improves clustering performance and network convergence speed.

Little works have focused on constrained clustering for big datasets; also, the studies in DNNs for clustering, with specific loss function that simultaneously extract features and clustering the data, are rare. The method improves the performance of big data clustering without using labels, and it is important because the data labeling is expensive and time-consuming, especially for big datasets.

Decision support systems developed using machine learning classifiers have become a valuable tool in predicting various diseases. However, the performance of these systems is adversely affected by the missing values in medical datasets. Imputation methods are used to predict these missing values. In this paper, a new imputation method called hybrid imputation optimized by the classifier (HIOC) is proposed to predict missing values efficiently.

The proposed HIOC is developed by using a classifier to combine multivariate imputation by chained equations (MICE), K nearest neighbor (KNN), mean and mode imputation methods in an optimum way. Performance of HIOC has been compared to MICE, KNN, and mean and mode methods. Four classifiers support vector machine (SVM), naive Bayes (NB), random forest (RF) and decision tree (DT) have been used to evaluate the performance of imputation methods.

The results show that HIOC performed efficiently even with a high rate of missing values. It had reduced root mean square error (RMSE) up to 17.32% in the heart disease dataset and 34.73% in the breast cancer dataset. Correct prediction of missing values improved the accuracy of the classifiers in predicting diseases. It increased classification accuracy up to 18.61% in the heart disease dataset and 6.20% in the breast cancer dataset.

The proposed HIOC is a new hybrid imputation method that can efficiently predict missing values in any medical dataset.

Rtsa-byugs, a massage oil from Bhutan, is a traditional herbal formula known for its anti-inflammatory properties and used in osteoarthritis treatment. This study investigates the efficacy of rtsa-byugs vs diclofenacgel in relieving knee pain in osteoarthritis patients.

A single-blind, randomized controlled trial was conducted amongst osteoarthritis knee patients at an orthopedic outpatient department of Thammasat University Hospital. Participants were randomly allocated to the rtsa-byugs (N = 31) or the Diclofenac gel (N = 31) group. Primary outcomes were assessed by the knee injury and osteoarthritis outcome scores (KOOS), visual analog scale (VAS) and goniometer at day 0, 1, 3, 7.

62 participants completed the study. The result of the KOOS scores demonstrated a significant improvement of symptoms at the end of the study in both treatment groups. Improvement of symptoms, pain, daily life living, sport and recreational score and quality of life assessment showed a significant difference from baseline (p < 0.001) within both groups. The quality of life score for the rtsa-byugs group increased significantly on day 3 and 7. The VAS score in both groups decreased with a significant difference from baseline to day 7. The mean value of extension of angle measurement was decreased in day 7, and the mean of flexion score increased in both groups when compared with the baseline.

The duration of the study was very limited and included a small sample consisting of men and women.

Rtsa-byugs is safe and effective in relieving pain from osteoarthritis of the knee and can be used as an alternative treatment for knee osteoarthritis.

This study aims to increase the understanding of the pregnancy-related information behavior (IB) of pregnant women in Estonia.

The research involved a quantitative research methodology consisting of a semi-structured questionnaire. Data was collected from pregnant Estonian women through a self-administered Web-based questionnaire using a convenience sampling during the period from January to February 2019. A total of 300 pregnant women answered the questionnaire. The data were analysed using statistical analysis and the results of the study were compared with the results of previous studies.

The three topics on which information was most frequently sought were: fetal development, use of medicines during pregnancy and symptoms of pregnancy. The main sources of information were the internet and the midwife. The most reliable and valuable source of information was a midwife. Health-related information was sought mainly because it helped women make decisions related to pregnancy and childbirth. A number of factors facilitate the information seeking process. In addition, widespread access to the internet and technological skills facilitated IB. The following factors hindered the search for information: the controversy and/or ambiguity of information published on the internet and the time spent searching for information. Most women used wearable technologies during pregnancy.

This study has several limitations. First, the weakness of online surveys is the potential lack of representativeness, as it excludes from the survey those who do not have access to or ability to use the internet for various reasons (Evans and Mathur, 2005; Limbu et al., 2021). Second, as most recruitment for the study took place online, there was a risk that those who did not use the internet could be excluded from the survey. Third, as the questionnaire was also shared in the Facebook news feed by the Women’s Clinic and Maternity Hospital of the East Tallinn Central Hospital, it may be that the respondents recruited through it more often used the support provided by medical professionals. Fourth, due to the volume limits of the study, it is not possible to present all the results of the study on the basis of socio-demographic characteristics and stage of pregnancy. Therefore, the findings cannot be generalized to the broader population and future studies should explore a larger and more representative populations.

This study will give some useful information to help to improve the services offered for pregnant women in Estonia.

The findings of this study may inform how to better support this target group.

There is a lack of research in Estonia that focuses on the IB of pregnant women and this research fills this gap.

The study endeavors to explore whether the financialization of agricultural commodities, traditionally viewed as a catalyst for price volatility, has any repercussions on food security in BRICS economies.

The empirical analysis employs the examination of three agricultural commodities, namely wheat, maize and soybean. Utilizing data from the Chicago Board of Trade on futures trading for these commodities, we focus on parameters such as annual trading volume, annual open interest contracts and the ratio of annual trading volume to annual open interest contracts. The study spans the period 2000–2021, encompassing pre- and post-financial crisis analyses and specifically explores the BRICS countries namely the Brazil, Russia, India, China and South Africa. To scrutinize the connections between financialization indicators and food security measures, the analysis employs econometric techniques such as panel data regression analysis and a moderating effects model.

The results indicate that the financialization of agricultural products contributes to the heightened food price volatility and has adverse effects on food security in emerging economies. Furthermore, the study reveals that the impact of the financialization of agricultural commodities on food security was more pronounced in emerging nations after the global financial crisis of 2008 compared to the pre-crisis period.

This paper seeks to draw increased attention to the financialization of agricultural commodities by presenting empirical evidence of its potential impact on food security in BRICS economies. The findings serve as a valuable guide for policymakers, offering insights to help them safeguard the security and availability of the world’s food supply.

Very few studies have explored the effect of financialization of agricultural commodities on food security covering a sample of developing economies, with sample period from 2000 to 2021, especially at the individual agriculture commodity level. Understanding the evolving effects of financialization is further improved by comparing pre and post-financial crisis times.

The main objective of this study is to assess the applicability and robustness of the information motivation behavioural skills (IMB) model in determining dietary supplement usage of pregnant and breastfeeding women. More specifically, we examine the indirect effects of online social capital and internet use for health information on dietary supplement usage through self-efficacy and the moderating role of educational attainment.

Data was collected from 415 pregnant and breastfeeding Italian women using a self-administered questionnaire. Hypotheses were tested using Hayes's (2013) PROCESS macro for SPSS.

Internet use for health information is directly associated with dietary supplement usage. Online social capital and internet use for health information positively influence dietary supplement usage through self-efficacy. However, the results from moderated mediation analyses show that the mediation effects are moderated by educational attainment so that indirect relationships were stronger among women with a lower level of education than among those with a higher level of education.

Dietary supplement marketers and public health agencies can develop and implement dietary supplement promotional materials and interventions by disseminating information through the internet and social media and by strengthening social ties on online networking sites.

The originality of this study lies in the use of the IMB model as a theoretical framework to examine the mediating role of self-efficacy and the moderating role of education in explaining the mechanism of how online social capital and internet use for health information influence dietary supplement usage.

This paper aims to concentrate on an efficient finite impulse response (FIR) filter architecture in combination with the differential evolution ant colony algorithm (DE-ACO). For the design of FIR filter, the evolutionary algorithm (EA) is found to be very efficient because of its non-conventional, nonlinear, multi-modal and non-differentiable nature. While focusing with frequency domain specifications, most of the EA techniques described with the existing systems diverge from the power related matters.

The FIR filters are extensively used for many low power, low complexities, less area and high speed digital signal processing applications. In the existing systems, various FIR filters have been proposed to focus on the above criterion.

In the proposed method, a novel DE-ACO is used to design the FIR filter. It focuses on satisfying the economic power utilization and also the specifications in the frequency domain.

The proposed DE-ACO gives outstanding performance with a strong ability to find optimal solution, and it has got quick convergence speed. The proposed method also uses the Software integrated synthesis environment (ISE) project navigator (p.28xd) for the simulation of FIR filter based on DE-ACO techniques.

This paper aims to evaluate the progress made in achieving sustainable development goal-2 (SDG 2) in India, with a focus on ending hunger, ensuring food security, improving nutrition and promoting sustainable agriculture. The assessment uses data from SDG Index reports, which offer a comprehensive overview of the advancements made by 28 states and 8 union territories (UTs) in India.

The evaluation is based on information derived from three editions of the SDG Index reports, initially published in 2018 and subsequently in 2019 and 2020. These reports provide a detailed analysis of the status and achievements of different states and UTs in relation to SDG 2. The categorization of states and UTs into aspirant, performer, front runner and achiever categories serves as a crucial framework for assessing the progress.

Despite concerted efforts by India, the majority of states and UTs are positioned in the aspirant and performer categories, suggesting that significant challenges persist in achieving SDG 2 targets. The results emphasize the necessity for stronger measures to elevate states and UTs to the categories of front-runners and achievers. The persistent challenges of malnutrition, hunger and their economic ramifications require immediate and strategic interventions to address these pressing concerns.

This paper contributes to the existing literature by providing a comprehensive analysis of the progress towards SDG 2 in India, using the insights from the SDG Index reports. The categorization framework used in this assessment offers a nuanced understanding of the challenges faced by different regions, highlighting the original contribution of this study. The findings underscore the urgency of targeted efforts to address malnutrition, hunger and related issues, emphasizing the importance of sustained commitment to achieving SDG 2 for the overall well-being of vulnerable populations.