• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3855-3867
• /
• 2022

Name separation (splitting full names into surnames and given names) is not a tedious task in a multiethnic country because the procedure for splitting surnames and given names is ethnicity-specific. Malaysia has multiple main ethnic groups; therefore, separating Malaysian full names into surnames and given names proves a challenge. In this study, we develop a two-phase framework for Malaysian name separation using deep learning. In the initial phase, we predict the ethnicity of full names. We propose a recurrent neural network with long short-term memory network-based model with character embeddings for prediction. Based on the predicted ethnicity, we use a rule-based algorithm for splitting full names into surnames and given names in the second phase. We evaluate the performance of the proposed model against various machine learning models and demonstrate that it outperforms them by an average of 9%. Moreover, transfer learning and fine-tuning of the proposed model with an additional dataset results in an improvement of up to 7% on average.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.47 no.1
• /
• pp.25-33
• /
• 2021

Objectives: Many conditions of the oral and maxillofacial region require hospitalization and in-patient care. The average length of stay (LOS) of these patients varies and is usually affected by multiple confounding variables. However, even with an increasing number of hospital admissions, published evidence on the factors that affect the LOS of oral and maxillofacial patients is lacking. Therefore, this study assessed the LOS of in-patients at the oral and maxillofacial surgery department of a government-funded, multi-specialty hospital in Malaysia, based on their reasons for admission and other factors. Materials and Methods: Our samples were collected retrospectively over a 5-year period and included patients with maxillofacial infections, post-trauma stabilization, facial bone fracture surgery, benign and malignant lesion surgery, dentoalveolar surgery, and other maxillofacial surgeries as reasons for admission. Factors potentially affecting LOS were also recorded, and their significance was determined using multiple logistic regression analyses. A P-value of less than 0.05 was considered to be statistically significant. Results: A total of 1,380 patients were included in this study. Most (84.5%) of our in-patients were of Malay ethnicity, and males outnumbered females in our sample by 502 subjects. The median LOS of our in-patients was 3 days. Sex, ethnicity, age, reason for admission, and American Society of Anesthesiology (ASA) classification were factors that significantly affected LOS. Conclusion: The median LOS reported in this study was 3 days. LOS was significantly affected by sex, ethnicity, age, reason of admission and ASA classification.

• Communications for Statistical Applications and Methods
• /
• v.26 no.1
• /
• pp.1-9
• /
• 2019

Various probabilistic methods have been proposed for using interpopulation allele frequency differences to infer the ethnic group of a DNA specimen. The selection of the statistical method is critical because the accuracy of the statistical classification results vary. For the ancestry classification, we proposed a new ancestry evaluation method that estimate the combined ethnicity index as well as compared its performance with various classical classification methods using two real data sets. We selected 13 SNPs that are useful for the inference of ethnic origin. These single nucleotide polymorphisms (SNPs) were analyzed by restriction fragment mass polymorphism assay and followed by classification among ethnic groups. We genotyped 400 individuals from four ethnic groups (100 African-American, 100 Caucasian, 100 Korean, and 100 Mexican-American) for 13 SNPs and allele frequencies that differed among the four ethnic groups. Additionally, we applied our new method to HapMap SNP genotypes for 1,011 samples from 4 populations (African, European, East Asian, and Central-South Asian). Our proposed method yielded the highest accuracy among statistical classification methods. Our ethnic group classification system based on the analysis of ancestry informative SNP markers can provide a useful statistical tool to identify ethnic groups.

• Culinary science and hospitality research
• /
• v.22 no.1
• /
• pp.70-77
• /
• 2016

The purpose of this research was to assess university students' nutrition knowledge, confidence, information sources and their body image. This study used an online survey engine to collect data from college students. The result of the correlation showed overall subjective knowledge had significant correlation with nutrition. Means of the BMI were compared among the demographic groups with regard to their ethnicity, classification, and age. Significant differences were found among demographic groups regarding the means of the BMI. These findings can enhance the extant literature on the universal applicability of the model and serve as useful references for further investigations within other health care or foodservice settings and for other health behavioral categories.

• Journal of Fashion Business
• /
• v.12 no.6
• /
• pp.34-45
• /
• 2008

This research was designed to find decision factors through color assortment planning process by Korean women's clothing merchandisers and to look for if there exists difference with American women's clothing merchandisers. A merchandise assortment is a collection of various quantities of styles, colors, sizes, and prices of related merchandise, usually grouped under one classification within a department. The subjects were 20 women's clothing merchandisers who work for clothing retail stores from 5 to 22 years in US and Korea. The authoring process was done for qualitative data analysis. The decision factors of color assortment planning were identified with four stages; information search, qualitative evaluation, quantitative evaluation, and selection. There were differences of color assortment decision factors due to different business types, business sizes, fashion-ability, sourcing ways, and merchandise turnover. Noticeable color assortment decision factor differences caused by country difference were not found except considering the target market ethnicity and skin color in US market. Korea merchandisers seem to be more sensitive to present sales data usages and spot order availability in color assortments because of more local production use than American merchandisers.

• Safety and Health at Work
• /
• v.5 no.3
• /
• pp.161-164
• /
• 2014

Obesity is a significant problem affecting United States (US) firefighters. While body mass index (BMI) is widely used to diagnose obesity, its use for this occupational group has raised concerns about validity. We examined rates and types of misclassification of BMI-based obesity status compared to body fat percentage (BF%) and waist circumference (WC). Male career firefighters (N = 994) from 20 US departments completed all three body composition assessments. Mean BMI, BF%, and WC were $29kg/m^2$, 23%, and 97 cm, respectively. Approximately 33% and 15% of BF%- and WC-defined obese participants were misclassified as non-obese (false negatives) using BMI, while 8% and 9% of non-obese participants defined by BF% and WC standards were identified as obese (false positives) using BMI. When stratified by race/ethnicity, Pacific Islanders showed high rates of false positive misclassification. Precision in obesity classification would be improved by using WC along with BMI to determine firefighters' weight status.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.9
• /
• pp.4517-4520
• /
• 2012

Introduction: Northeastern Iran is known as a high risk area of upper gastrointestinal cancers. Recent reports have suggested a declining trend for these cancers as well as an increase in the incidence of other malignancies including breast cancer. Our present aim was to describe the epidemiological pattern of breast cancer in this region during 2004-2009. Methods: All new cancer cases from public and private diagnostic and therapeutic centers of Golestan province were registered. A structured questionnaire was prepared and used based on the standerds of the International Association of Cancer Registries. The international classification of diseases for oncology was considered for coding. Age standardized incidence rates (ASR) of breast cancer were calculated. Results: A total of 11,038 new cancer cases were registered during 2004-2009, of which, 1,101 (10%) were females with breast cancer. The median age of the breast cancer patients was 46 years. The ASR for breast cancer was 28 per 100,000 person-years. We found an unusual rapid increase in breast cancer rate at the age of 25 years. The ASR of breast cancer was significantly lower in females from Turkmen ethnicity and those from rural areas(P value <0.01). Conclusion: Our study showed high rate of breast cancer in Golestan province of Iran. We found an unusual peak of breast cancer in young women. So, the age of starting screening programs may need to be revised in this area. The rate of breast cancer was significantly lower in women from Turkmen ethnicity. Further studies are warranted to clarify the role of important determinants, especially regarding the ethnic disparity, on breast cancer in this region.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.11-20
• /
• 2024

While artificial neural networks are adept at identifying patterns, they can struggle to distinguish between actual correlations and false associations between extracted facial features and criminal behavior within the training data. These associations may not indicate causal connections. Socioeconomic factors, ethnicity, or even chance occurrences in the data can influence both facial features and criminal activity. Consequently, the artificial neural network might identify linked features without understanding the underlying cause. This raises concerns about incorrect linkages and potential misclassification of individuals based on features unrelated to criminal tendencies. To address this challenge, we propose a novel region-based training approach for artificial neural networks focused on criminal propensity detection. Instead of solely relying on overall facial recognition, the network would systematically analyze each facial feature in isolation. This fine-grained approach would enable the network to identify which specific features hold the strongest correlations with criminal activity within the training data. By focusing on these key features, the network can be optimized for more accurate and reliable criminal propensity prediction. This study examines the effectiveness of various algorithms for criminal propensity classification. We evaluate YOLO versions YOLOv5 and YOLOv8 alongside VGG-16. Our findings indicate that YOLO achieved the highest accuracy 0.93 in classifying criminal and non-criminal facial features. While these results are promising, we acknowledge the need for further research on bias and misclassification in criminal justice applications

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.8
• /
• pp.3687-3693
• /
• 2012

Objective: The current meta-analysis was performed to address a more accurate estimation of the association between glutathione S-transferase P1 (GSTP1) codon 105 polymorphism and risk of gastric cancer (GC), which has been widely reported with conflicting results. Methods: A comprehensive literature search was conducted to identify all the relevant studies. Fixed or random effect models were selected based on the heterogeneity test. Publication bias was estimated using Begg's funnel plots and Egger's regression test. Results: A total of 20 studies containing 2,821 GC cases and 6,240 controls were finally included in the analyses. Overall, no significant association between GSTP1 polymorphism and GC risk was observed in worldwide populations. However, subgroup analysis stratified by ethnicity showed that GSTP1 polymorphism was significantly associated with increased risk of GC in Asians (G vs. A, OR = 1.273, 95%CI=1.011-1.605; GG vs. AA, OR=2.103, 95%CI=1.197-3.387; GG vs. AA+AG, OR =2.103, 95%CI=1.186-3.414). In contrast, no significant association was found in Caucasians in any genetic models, except for with AG vs. AA (OR=0.791, 95%CI=0.669-0.936). Furthermore, the GSTP1 polymorphism was found to be significantly associated with GC in patients with H. pylori infection and in those with a cardiac GC. Subgroup analysis stratified by Lauren's classification and smoking status showed no significant association with any genetic model. No studies were found to significantly influence the pooled effects in each genetic mode, and no potential publication bias was detected. Conclusion: This meta-analysis suggested that the GSTP1 polymorphism might be associated with increased risk of GC in Asians, while GSTP1 heterozygote genotype seemed to be associated with reduced risk of GC. Since potential confounders could not be ruled out completely, further studies are needed to confirm these results.