Univariate Manner Research Articles

P-119 Factors affecting male-to-female ratio at birth in IVF/ICSI cycles

Abstract Study question Are there any factors during an IVF cycle that can influence the ratio of male or female preimplantation embryos? Summary answer Semen preparation technique significantly influences the male-female ratio of newborns through IVF-ICSI with a greater proportion of boys with gradients and girls with swim up. What is known already Although some works have related the fertilization technique or the transfer of blastocysts with the male-female ratio in those born through assisted reproduction, there are limited studies that investigate the relationships of the various factors involved during an IVF/ICSI cycle with the ratio male-female at birth. Furthermore, the number of studies that looked at the effect of embryo morphokinetics in sex ratio at birth, produced contradictory results. Study design, size, duration Retrospective, multicenter study at seven reproductive units belonging to the same center in Spain. The study included 202 patients who underwent IVF/ICSI treatment between January 2022 and December 2022, ensuring that 100% implantation was obtained. All cycles were accomplished with time-lapse, and the transfers were performed at the blastocyst stage. The sex was confirmed at birth. Participants/materials, setting, methods Sex ratios of 223 live births were compared regarding to fertilization method (IVF or ICSI), age, culture medium, embryo morphokinetics (t2, t3, t4,t5,tM,tSB,tBc,cc2,s2), twinship, origin of oocytes and sperm, embryo quality and sperm preparation technique (swim-up vs gradients). The Student’s T test was used for metric variables and the χ2 test for dichotomous variables (p < 0.05). To assess if the rest of the metric variables influenced sex, the Kolmogorov-Smirnov test and the Pearson test were used. Main results and the role of chance 223 live births were obtained: 181 single births after the transfer of one blastocyst and 42 double births of the same sex after the transfer of two blastocysts. Among the 223 newborns included in the study, a statistically significant predominance (p < 0.05) of males was found: 58.3% (95%CI:51.8-64.8%) of boys (n:130) compared to 41.7% (95%CI:35.2-48.2%) of girls (n :93). The mean age of the patients was 38.3 years (SD: 4.87), with no significant differences found regarding the sex ratio, as well as with the fertilization technique (p = 0.937), culture medium (p = 0.096), twinning (p = 0.222), the origin of the oocytes (p:0.608), the origin of the semen (p:0.721) and embryo quality (P:0.186). A statistically significant relationship was found between the sex of the newborn and the semen preparation technique (62.1% of male with gradients versus 32.1% with swim up, p:0.003), which was confirmed using a multivariate binary logistic regression model (p:0.0200). Analyzing each of the parameters obtained from the time lapse with respect to the sex of the newborns in a univariate manner with Student’s T for independent samples no significant differences were found in the division times studied or in the times of the cell cycle and synchrony. Limitations, reasons for caution The main limitation is the necessity of a larger sample size and to further investigate the reasons for these results. Further studies with standardized culture conditions and well-justified inclusion criteria are needed to reach robust and reliable conclusion. Wider implications of the findings While the study needs for more extensive sample size for future research, is the first time to suggest that method of sperm preparation may have an impact on the sex ratio at birth. Understanding which factors within ART process can affect sex ratio remain important considerations. Trial registration number not applicable

Prevalence and risk factors related to intestinal parasitosis in children under 18 years of age in four populations of Colombia: a cross-sectional study

Objective: To identify the profile of intestinal parasitosis in children of four populations in the municipalities of Quibdó, Apartadó, Guachené, and Granada, Colombia, in 2012.
 Material and methods: A cross-sectional study was conducted using a secondary source of information, in which sociodemographic factors associated with the presence of parasites were analyzed in a univariate and bivariate manner.
 Results: A total of 240 individuals were analyzed. Two thirds of them were parasitized. The most frequent species were Entamoeba histolytica/dispar (22.9%), Endolimax nana (19.2%), Blastocystis hominins (19.2%), and Giardia intestinalis (20.8%). An association between inadequate excreta disposal (latrine or septic tank) and the presence of parasitic colonization was found with a prevalence ratio (PR) of 1.34 [1.14, 1.59] (p=0.005). Similarly, housing construction with wood or baharequewas 1.31 times more frequent in subjects with parasitic forms in their stool samples than those with brick houses.Discussion: A higher frequency of intestinal parasites was found for the different age groups compared to several reports worldwide and in Latin America. The most frequent species of parasites were similar to those reported in the literature.Conclusions: Isolated populations in Colombia, such as those studied, have a higher frequency of intestinal parasites than other populations.

Investigation the Effect of Covıd-19 Pandemic in The Sales for Online Education Using Machine Learning Methods

Due to the pandemic which is the cause of the COVID-19 virus that emerged in 2019, many educational institutions had to follow online (remote) education. The situation in which the content of the pandemic occurred was also the reason for the education preferences of the users. The aim of this study is to analyze the effect of the pandemic, which includes the number of registered users of one of the online education platforms operating in Turkey thanks to machine learning, on distance education sales, and to create strategies by making sales forecasts for the future. Seven independent and one dependent variable were used to make sales forecasts using the data of the education structure. For accurate modelling, machine learning methods were first applied for decision analytics in a univariate manner and then multivariate applied and the applied methods were tested for error. By testing the success of the prediction models created with machine learning used in the study; 91.43% for support vector machine (SVM), 92.02% for multi-layer perceptron (MLP), and 96% for Long / Short Term Memory (LSTM). K-Folds cross validation method was also used for the success return of the established model.

Transabdominal Management of Epiphrenic Diverticula in the Setting of Achalasia: A Single-center Review.

The perioperative and functional outcomes of patients with epiphrenic diverticula (ED) on a background of achalasia managed via a minimally invasive transabdominal approach are under-reported. We describe our center's experience over 10 years of treating such patients. A single-center, retrospective chart of a prospectively maintained hospital database was performed. All patients with a diagnosis of ED and manometrically proven achalasia were identified. Demographic, clinical, and surgical data were extracted from the institution's medical records. Patients were stratified by whether they underwent myotomy only or myotomy plus diverticulectomy and compared in a univariate manner. There were 18 patients who met the inclusion criteria. The median age of the cohort was 67.1 years (range 53.1 to 77.8), the maximal size of the diverticula was 3.5cm (range 2.0 to 7.0), and the distance of the proximal lip of the diverticulum to the incisors was 33.5cm (range 28.0 to 38.0). In terms of surgical intervention, 14 patients (77.8%) underwent myotomy plus diverticulectomy, and 4 (22.2%) underwent myotomy alone. The duration of surgery was significantly longer in the former (177.5 vs. 75.0min, P =0.031). In total, 9/18 (50.0%) of patients were discharged on the day of surgery. There was a trend to more major postoperative complications following diverticulectomy plus myotomy, with 2/13 (15.4%) patients suffering staple line leaks. Excellent long-term functional outcomes were achieved, with 81.3% of patients having sustained resolution of their symptoms. Laparoscopic transabdominal approach for the treatment of ED offers an acceptable risk profile and favorable functional outcomes in patients with underlying achalasia.

The Effect of Birth Ball Exercise on the Progress of Labor During the First Active Phase at PONED (Basic Emergence Neonatal Obstetric Services) UPTD DTP Pedes Health Center, Karawang Regency, Indonesia

Background.Prolonged parturition or labor that lasts longer than usual can increase the risk of complications and the potential for maternal death. The birth ball exercise, also known as the birth ball exercise or the pregnancy ball exercise, can help harness the influence of gravity to induce labor progress. This study aimed to assess the effect of birth ball exercises on the progress of labor during the first active phase at the PONED UPTD DTP Pedes Health Center, Karawang Regency, Indonesia. Methods.This study is an experimental study, where as many as 30 research subjects participated in this study. Analysis of the progress of labor was carried out using SPSS software in a univariate and bivariate manner. Results. The results of the study showed that the birth ball exercise had an effect on the progress of labor with a p-value = 0.002 (p <0.05). Conclusion, there is an influence of birth ball exercises on the progress of labor at PONED UPTD DTP Pedes Health Center, Karawang Regency, Indonesia.

The Effect of Birth Ball Exercise on the Progress of Labor During the First Active Phase at PONED (Basic Emergence Neonatal Obstetric Services) UPTD DTP Pedes Health Center, Karawang Regency, Indonesia

Prolonged parturition or labor that lasts longer than usual can increase the risk of complications and the potential for maternal death. The birth ball exercise, also known as the birth ball exercise or the pregnancy ball exercise, can help harness the influence of gravity to induce labor progress. This study aimed to assess the effect of birth ball exercises on the progress of labor during the first active phase at the PONED UPTD DTP Pedes Health Center, Karawang Regency, Indonesia. This study is an experimental study, where as many as 30 research subjects participated in this study. Analysis of the progress of labor was carried out using SPSS software in a univariate and bivariate manner. The results of the study showed that the birth ball exercise had an effect on the progress of labor with a p-value = 0.002 (p <0.05). In conclusion, there is an influence of birth ball exercises on the progress of labor at PONED UPTD DTP Pedes Health Center, Karawang Regency, Indonesia.

The 8th Edition TNM Stage Reclassification of T4 Non-Small Cell Lung Cancer: A Granular Examination of Short and Long-Term Outcomes

IntroductionWhilst the American Joint Committee on Cancer 7th edition (AJCC7) classified pT4 non–small-cell lung cancers (NSCLC) as those with extra-pulmonary invasion, the revised 8th edition (AJCC8) included tumors > 7cm regardless of extra-pleural spread. We examined perioperative and long-term outcomes of classical T4 definitions with patients whose tumors were greater than 7cm without extra-pulmonary invasion. Materials and methodsA retrospective single center cohort study was performed. All consecutive patients with pT4 lesions between 2011 and 2018 were identified based on either the AJCC7 or AJCC8 classification. Clinicopathological variables were extracted and compared in a univariate manner. A multivariate Cox regression analysis was performed to assess factors associated with overall survival. ResultsForty patients were allocated to AJCC7 and 118 to AJCC8. Patients in the former were more likely to have positive lymph nodes, synchronous metastasis, multifocal disease and lymphovascular invasion. AJCC7 patients were more likely to undergo pneumonectomy despite significantly more being treated with neoadjuvant therapy. Ninety-day mortality was higher in the AJCC7 group. There was no difference in long-term overall survival. On multivariate analysis male gender, squamous cell histology and increasing tumor size were associated with an increased risk of death. ConclusionAlthough long-term outcomes were similar, the heterogenicity within the AJCC8 classification emphasizes the need to contextualize the perioperative outcomes for patients with pT4 NSCLC. These data are important for future iterations of the TNM classification in view of emerging neoadjuvant options for patients with cT4 operable NSCLC.

The Potential of the Problem Posing Method on Mathematics Learning Outcomes: A Study in Grade IX-G Students of SMPN 244 Jakarta, Indonesia

Mathematics is still one of the subjects that is less attractive to students. Students often think that mathematics is difficult or even boring. The posing method is one of the efforts that can be developed in order to be a solution in the process of teaching mathematics so that mathematics is no longer something difficult and frightening. A posing method is an approach to learning mathematics where students are not only oriented to solving a problem. However, students participate in making questions. This study aimed to determine the potential of the posing method in improving mathematics learning outcomes in grade IX-G students of SMPN 244 Jakarta, Indonesia. This study is an experimental study with a pre-post test design approach. A total of 36 research subjects participated in this study. The posing method intervention in this study consisted of 2 cycles, with 2 meetings in each cycle. Furthermore, re-intervention and evaluation of the implementation of cycle II as in cycle I. The success of the posing method is carried out by assessing student learning outcomes. Data analysis was carried out in a univariate manner by comparing the average and frequency of student learning outcomes. The results of the study showed that there was a shift in learning outcomes from those that were initially at a score of 5 and then experienced improvement after the posing method was applied to the majority of scores 8 and 9. In conclusion, the posing method has the potential to improve mathematics learning outcomes in grade IX-G students of SMPN 244 Jakarta, Indonesia.

Multivariate random forest for digital soil mapping

In digital soil mapping (DSM), soil maps are usually produced in a univariate manner, that is, each soil map is produced independently and therefore, when multiple soil properties are mapped the underlying dependence structure between these soil properties is ignored. This may lead to inconsistent predictions and simulations. For example, soil organic carbon (SOC) and total nitrogen (TN) maps produced independently may show unrealistic carbon–nitrogen (C:N) ratios. In the last decade the production of soil maps with machine learning models has become increasingly popular as these models are able to capture complex non-linear relationships between soil properties and environmental covariates. However, producing soil maps with multivariate machine learning models is still lacking and requires much investigation in DSM. In this paper we present the combined modelling of multiple soil properties with a multivariate random forest (MRF) model. We applied this model to mapping SOC and TN, and we compared it with results of two separate univariate random forest (RF) models. The comparison was done by means of stochastic simulations determined by sampling from the conditional distributions of the soil properties, given the covariates, as estimated by quantile regression forest. The results show that the MRF model is superior in terms of maintaining the dependence structure between SOC and TN, and consequently, is also able to produce more realistic C:N ratios. The models were also compared on the basis of prediction accuracy using commonly used accuracy metrics such as the root mean square error (RMSE). We found that the accuracy of the MRF model (RMSE-SOC=40.04, RMSE-TN=2.26, RMSE-CN=3.58) is comparable to that of the univariate RF models (RMSE-SOC=39.76, RMSE-TN=2.26, RMSE-CN=3.65). We performed the same comparisons between a regression co-kriging model and two separate regression kriging models, and made similar conclusions.

Overview of COVID-19 Vaccination Status in Patients Infected with COVID-19 at the Royal Prima General Hospital Medan

Since the start of the COVID-19 pandemic, attempts have been made to provide acquired immunity against COVID-19. Monitoring and evaluating the efficacy and safety of the COVID-19 vaccine is an important process that must always be carried out in order to optimize the control of the spread of COVID-19 infection. This study aimed to provide an overview of the status of COVID-19 vaccination in patients infected with COVID-19 at the Royal Prima General Hospital, Medan, Indonesia. This study was a descriptive observational study. A total of 100 subjects participated in this study. Data analysis was performed using SPSS version 25 in a univariate manner. The majority of patients who have been vaccinated against COVID-19 only experience mild symptoms of COVID-19. The majority of vaccine brands used by confirmed COVID-19 patients are Sinovac. The majority of patients who have received 2 doses of vaccination are still at risk of being infected with COVID-19. The majority of patients who received the COVID-19 vaccination experienced a low clinical degree when infected with COVID-19.

Profile of Side Effects of Chemotherapy in Non-Small Cell Lung Cancer Patients (NSCLC) Undergoing Chemotherapy at Dr. M. Djamil General Hospital, Padang, Indonesia

Background: Chemotherapy is one of the treatment options for lung cancer at any stage. Side effects due to chemotherapy are still a problem in the treatment of lung cancer patients. Chemotherapy drugs have different side effects according to their pharmacokinetics and pharmacodynamics. This study aimed to determine the side effects of both hematological and non-hematological chemotherapy in non-small cell lung cancer patients treated at the lung ward of Dr. M. Djamil General Hospital, Padang, Indonesia, from 2017 to 2019.
 Methods: This was a descriptive observational study, a total of 42 study subjects. The study subjects were non-small cell lung cancer patients undergoing first-line chemotherapy. Sociodemographic, clinical, and laboratory data analysis was carried out with the help of SPSS software in a univariate manner.
 Results: The study subjects were mostly male (85.36%), the age range of 40-60 years (66.67%), at risk of exposure from work (45.23%), smokers (59.52%), had a history of pulmonary TB (11.9%), history of COPD (2.38%), history of malignancy of other organs (2.38%) with the most cell type being adenocarcinoma (54.76%). The most common hematological side effects were first-degree anemia (21.43%) and first-degree leukopenia (21.43%). The most non-hematological side effects were first-degree alopecia (90.48%), followed by first-degree nausea and vomiting (78.57%).
 Conclusion: Chemotherapy side effects were found in all regimens given with mild degrees. The side effects obtained were in the form of hematological and non-hematological side effects.

Description of clean and healthy behavior in prevention of Covid – 19 at students of science University Cut Nyak Dhien in 2022

Most of the transmission of COVID - 19 occurs through the touch of hands due to the lack of people in implementing clean and healthy living behaviors (PHBS) as the cause of the rapid spread of the virus. PHBS is a form of embodiment of a healthy life orientation in individual, family and community culture, which aims to improve, maintain and protect their health both physically, mentally, spiritually and socially. The research aims to describe the behavior of students in Science University of Cut Nyak Dhien regarding PHBS in preventing COVID-19. This type of research is a descriptive survey research. The sample in this study was students in Science University of Cut Nyak Dhien is total sampling with 75 respondents. The data were processed and analyzed in a univariate manner. The results showed that the majority of respondents had sufficient knowledge about PHBS, amounting to 45 (60.0%), and a minority of respondents who had less knowledge, numbering 10 (13.3%), negative attitudes about PHBS, amounting to 39 (52.0%). , and a small proportion of positive attitudes amounted to 36 (48.0%), unskilled about PHBS 70 (93.3%), and a minority of skilled respondents amounted to 5 (6.7%). Clean and Healthy Living Behavior according to the Health Protocol really helps to prevent the transmission of COVID-19, higher education plays an important role in providing information and awareness for students to apply PHBS in lifestyle.

Comparison of Outcomes in Critically Ill Patients Installed with Mechanical Ventilation Performed Early and Late Tracheostomy at Dr. M. Djamil General Hospital Padang

Background: Tracheostomy is an alternative that is widely used as airway access after the use of a ventilator in the care of critically ill patients. Several factors are known to influence the outcome in patients undergoing tracheostomy. This study aimed to compare the outcomes of critically ill patients installed with mechanical ventilation performed early and late tracheostomy in Dr. M Djamil General Hospital, Padang, Indonesia.
 Methods: This study was an analytical observational study with a cross-sectional approach. A total of 97 research subjects participated in this study. Data analysis was carried out with the help of SPSS software in a univariate and bivariate manner between tracheostomy time (early and late) with patient outcomes in the form of death and length of stay.
 Results: There was a statistical difference in the mortality rate in critically ill patients with mechanical ventilation performed early and late tracheostomy, p = 0.014. There is a statistical difference in the length of stay in the intensive care unit in critically ill patients with mechanical ventilation performed early and late tracheostomy with p = 0.000.
 Conclusion: There are differences in outcomes in the form of mortality and length of stay in critically ill patients who have tracheostomy installed at Dr. M. Djamil General Hospital Padang, Indonesia.

Sample size requirement for achieving multisite harmonization using structural brain MRI features

When data is pooled across multiple sites, the extracted features are confounded by site effects. Harmonization methods attempt to correct these site effects while preserving the biological variability within the features. However, little is known about the sample size requirement for effectively learning the harmonization parameters and their relationship with the increasing number of sites. In this study, we performed experiments to find the minimum sample size required to achieve multisite harmonization (using neuroHarmonize) using volumetric and surface features by leveraging the concept of learning curves. Our first two experiments show that site-effects are effectively removed in a univariate and multivariate manner; however, it is essential to regress the effect of covariates from the harmonized data additionally. Our following two experiments with actual and simulated data showed that the minimum sample size required for achieving harmonization grows with the increasing average Mahalanobis distances between the sites and their reference distribution. We conclude by positing a general framework to understand the site effects using the Mahalanobis distance. Further, we provide insights on the various factors in a cross-validation design to achieve optimal inter-site harmonization.

Clusters based on immune markers in a Lithuanian asthma cohort study

Objective Asthma is divided into various distinct phenotypes on the basis of clinical characteristics, physiological findings, and triggers, and phenotyping is usually performed in a hypothesis-driven univariate manner. However, phenotyping can also be performed using computer algorithms to evaluate hypotheses-free relationships among many clinical and biological characteristics. We aimed to identify asthma phenotypes based on multiple demographic, clinical, and immunological characteristics. Methods Cluster analysis in R v3.5.0 was performed using asthma patient data. A total of 170 adult patients with asthma (diagnosed according to the GINA recommendations) were recruited to the study. All patients completed questionnaires about their smoking history and underwent physical examination, spirometry, skin-prick test, blood sample collection to evaluate peripheral blood cell counts and serum IgE, periostin, and interleukin (IL)-33 levels, as well as body mass index measurements. Data normality was checked with histograms and QQ plots. Hierarchical clustering was performed using Ward’s linkage with Ward’s clustering criterion. The optimal number of clusters was validated using the Dunn criterion as well as by comparing different clustering algorithms using the clValid package. Results Three clusters characterizing asthma phenotypes were identified: (1) early-onset, highly atopic, and eosinophilic asthma associated with male sex and high levels of IL-33 and periostin; (2) late-onset, eosinophilic asthma associated with female sex and low levels of IL-33 and periostin; and (3) late-onset, obese, neutrophilic asthma associated with female sex, persistent airway obstruction, and very low IL-33 and periostin levels.

Factors influencing participation in psychosocial programming among orthopaedic trauma patients with PTSD

IntroductionPost Traumatic Stress Disorder (PTSD) commonly occurs following acute trauma. Post-injury outcomes are negatively impacted by PTSD. Trauma Recovery Services (TRS) programming was developed at our institution in 2013 to provide psychosocial programming that increases patient satisfaction with care and ability to return to work and decreases PTSD symptoms. We sought to identify factors that influence patients’ decision to participate in programming. MethodsOver a 3-year period at a single, urban level 1 trauma center, 172 patients over the age of 18 screened positive for PTSD on the validated PTSD checklist for DSM-5 (PCL-5) screening tool. Demographic, socioeconomic, injury, and medical comorbidity information was collected. Variables were initially compared in a univariate manner via Chi-squared, Fisher exact, t-test, or Mann-Whitney U, as appropriate. Variables that had a p-value <0.2 on univariate analysis were entered into a backward stepwise logistic regression model to identify independent predictors of participation in TRS programming. ResultsMean age was 37.8 years. 70.1% of patients were male. The most common mechanisms of injury were gunshot wound (33.7%), motor vehicle crash (19.0%), and burn. 33.5% of patients participated in TRS programming. Nine predictors had p<.2 on univariate analysis and were entered into the stepwise regression model. Four predictors remained in the final model. Patients with private insurance (RR=2.2, p=.038), high school diploma or greater (RR=1.53, p=.002; Table 1), and PCL-5 score greater than 50 were more likely to participate in TRS programming (RR=1.42, p=.046). Patients who live 20 or more minutes away by car from TRS were less likely to participate in programming (RR=0.47, p=.065). DiscussionPatients with more severe PTSD, higher levels of education, and private insurance were more likely to participate in TRS programming. Participation in TRS and similar psychosocial programs may be improved by minimizing the participant's potential commute to the program location.

Joint hub identification for brain networks by multivariate graph inference

Recent developments in neuroimaging allow us to investigate the structural and functional connectivity between brain regions in vivo. Mounting evidence suggests that hub nodes play a central role in brain communication and neural integration. Such high centrality, however, makes hub nodes particularly susceptible to pathological network alterations and the identification of hub nodes from brain networks has attracted much attention in neuroimaging. Current popular hub identification methods often work in a univariate manner, i.e., selecting the hub nodes one after another based on either heuristic of the connectivity profile at each node or predefined settings of network modules. Since the topological information of the entire network (such as network modules) is not fully utilized, current methods have limited power to identify hubs that link multiple modules (connector hubs) and are biased toward identifying hubs having many connections within the same module (provincial hubs). To address this challenge, we propose a novel multivariate hub identification method. Our method identifies connector hubs as those that partition the network into disconnected components when they are removed from the network. Furthermore, we extend our hub identification method to find the population-based hub nodes from a group of network data. We have compared our hub identification method with existing methods on both simulated and human brain network data. Our proposed method achieves more accurate and replicable discovery of hub nodes and exhibits enhanced statistical power in identifying network alterations related to neurological disorders such as Alzheimer's disease and obsessive-compulsive disorder.

Decoding of semantic categories of imagined concepts of animals and tools in fNIRS

Objective. Semantic decoding refers to the identification of semantic concepts from recordings of an individual’s brain activity. It has been previously reported in functional magnetic resonance imaging and electroencephalography. We investigate whether semantic decoding is possible with functional near-infrared spectroscopy (fNIRS). Specifically, we attempt to differentiate between the semantic categories of animals and tools. We also identify suitable mental tasks for potential brain–computer interface (BCI) applications. Approach. We explore the feasibility of a silent naming task, for the first time in fNIRS, and propose three novel intuitive mental tasks based on imagining concepts using three sensory modalities: visual, auditory, and tactile. Participants are asked to visualize an object in their minds, imagine the sounds made by the object, and imagine the feeling of touching the object. A general linear model is used to extract hemodynamic responses that are then classified via logistic regression in a univariate and multivariate manner. Main results. We successfully classify all tasks with mean accuracies of 76.2% for the silent naming task, 80.9% for the visual imagery task, 72.8% for the auditory imagery task, and 70.4% for the tactile imagery task. Furthermore, we show that consistent neural representations of semantic categories exist by applying classifiers across tasks. Significance. These findings show that semantic decoding is possible in fNIRS. The study is the first step toward the use of semantic decoding for intuitive BCI applications for communication.

COMMERCIAL SEX WORKER COMPLIANCE WITH USING CONDOMS IN THE LOCALIZATION OF MANGROVE BAY, BATAM CITY

Background : According to the World Health Organization (WHO) HIV continues to be a global public health problem, claiming more than 70 million people are infected with the HIV virus and around 35 million people have died. In 2015, approximately 1.1 (940 000-1300000) million people have died due to being infected with the HIV virus. There were an estimated 36.7 (34.0-39.8) million people living with HIV at the end of 2016. Globally, Sub-Saharan Africa is the most affected region, with nearly 1 in 25 adults living with HIV. (WHO 2016). The purpose of this study was to determine the compliance of commercial sex workers on using condoms in the localization of Teluk Bakau, Batam City. Method : This study used a descriptive research design. The location of this research was carried out in the localization of Teluk Bakau, Batam City. The population in this study were all commercial sex workers (CSWs) in the Teluk Bakau brothels with a total of 95 people. The sample is an object under study and is considered to represent the entire population, here the writer uses a purposive technique, namely by means of sampling based on criteria. The measuring instrument in this study using a questionnaire. This analysis was carried out on each variable. These results are in the form of distribution and percentage of each variable. Data analysis was carried out in a univariate manner by looking at the results of the frequency calculation and the presentation of the results which could later be used as benchmarks for discussion and conclusions. Results and conclusions : It can be seen that the compliance of CSWs using condoms in the Bakau Bay brothel, Batam City is the majority of the majority behave obediently as many as 46 respondents (93.9%)

Unified Univariate-Neural Network Models for Lithium-Ion Battery State-of-Charge Forecasting Using Minimized Akaike Information Criterion Algorithm

Lithium-Ion batteries require step-ahead information to apply contingency plans to prevent them from operating beyond their safe operation thresholds in grid storage and electric vehicle applications. Recently, machine learning techniques have been increasingly applied to forecast one such battery information metric, State-of-Charge % ( SOC ). Conventional standalone machine learning techniques applied in recent works suffer from an accuracy standpoint and thus have been replaced by high-fidelity hybrid machine learning techniques. Existing works on hybrid techniques either perform in-sample predictions, provide limited information of the underlying model, or do not consider varying charging-discharging rate (C-rate) dynamics of the battery. To address this issue, this article presents unified SOC forecasting models using a Minimized Akaike Information Criterion ( ${m}$ -AIC) algorithm. Initially, the ${m}$ -AIC algorithm is used in a standalone manner to precisely tune and search ARIMA (Autoregressive Integrated Moving Average) terms’ order automatically to accurately forecast the battery’s current, voltage, and SOC parameters in a univariate manner at a lower C-rate from given C-rates. The ${m}$ -AIC algorithm based univariate models’ ( m-AIC ) accuracy is further enhanced by first modeling and unifying with Multilayer Perceptron (MLP) and then with Nonlinear Autoregressive Neural Network with external input (NARX) neural networks respectively using the previously forecasted parameters (from m-AIC ). This results in unified-MLP ( u- MLP) and unified-NARX ( u- NARX) models which provide higher accuracy out-of-sample SOC forecasting at the lower C-rate for different optimizer variants. Results show that the proposed u- MLP and u- NARX models reduce the mean squared error to 0.1048% and 0.0175% in comparison to their standalone counterparts which show the lowest corresponding error values of 0.271% and 0.0236% respectively. Furthermore, an additional reference univariate model, Holt-Winters Exponential Smoothing (HWES), is analyzed (by replacing m-AIC ) for a comparative performance evaluation in both standalone and unified manners. Recommendations for usage of the preferred respective models in either manner for SOC forecasting are also presented based on epochs and error values.