Coupling Analysis of Multiple Machine Learning Models for Human Activity Recognition

Artificial intelligence(AI)technology has become integral in the realm of medicine and healthcare,particularly in human activity recognition(HAR)applications such as fitness and rehabilitation tracking.This study introduces a robust coupling analysis framework that integrates four AI-enabled models,combining both machine learning(ML)and deep learning(DL)approaches to evaluate their effectiveness in HAR.The analytical dataset comprises 561 features sourced from the UCI-HAR database,forming the foundation for training the models.Additionally,the MHEALTH database is employed to replicate the modeling process for comparative purposes,while inclusion of the WISDM database,renowned for its challenging features,supports the framework’s resilience and adaptability.The ML-based models employ the methodologies including adaptive neuro-fuzzy inference system(ANFIS),support vector machine(SVM),and random forest(RF),for data training.In contrast,a DL-based model utilizes one-dimensional convolution neural network(1dCNN)to automate feature extraction.Furthermore,the recursive feature elimination(RFE)algorithm,which drives an ML-based estimator to eliminate low-participation features,helps identify the optimal features for enhancing model performance.The best accuracies of the ANFIS,SVM,RF,and 1dCNN models with meticulous featuring process achieve around 90%,96%,91%,and 93%,respectively.Comparative analysis using the MHEALTH dataset showcases the 1dCNN model’s remarkable perfect accuracy(100%),while the RF,SVM,and ANFIS models equipped with selected features achieve accuracies of 99.8%,99.7%,and 96.5%,respectively.Finally,when applied to the WISDM dataset,the DL-based and ML-based models attain accuracies of 91.4%and 87.3%,respectively,aligning with prior research findings.In conclusion,the proposed framework yields HAR models with commendable performance metrics,exhibiting its suitability for integration into the healthcare services system through AI-driven applications.

Lower serum folate is associated with development and invasiveness of gastric cancer

AIM: To evaluate the associations of serum folate levelwith development, invasiveness and patient survival of gastric cancer. METHODS: In this nested case-control study, patients with newly diagnosed gastric cancer undergoing gastrectomy were enrolled, and patients receiving chemotherapy prior to surgery, with other concurrent malignancy, or of the aboriginal and alien populations were excluded. In total, 155 gastric cancer patients and 149 healthy controls were enrolled for determination of serum folate levels and their correlation with gastric cancer. Using the median value of serum folate computed among the overall population as the cutoff value, the associations between serum folate and gastric cancer in all cases and different age and gender subgroups were analyzed by multivariate logistic regression analysis. In the patient cohort of gastric cancer, receiver-operating characteristic analyses were performed to calculate the best cutoff values of serum folate, and the associations between serum folate levels and clinicopathological features were further analyzed by multivariate regression analysis. Survival analyses were conducted using the Cox proportional hazards model.RESULTS: The mean serum folate level was significantly lower in gastric cancer patients than that in controls(3.71 ± 0.30 ng/mL vs 8.00 ± 0.54 ng/mL, P < 0.01), and folate levels were consistently lower in gastric cancer patients regardless of age and gender(all P < 0.01). Using the median serum folate value as the cutoff value, low serum folate was significantly associated with gastric cancer risk in the whole population(OR = 19.77, 95%CI: 10.54-37.06, P < 0.001) and all strata(age < 60 years OR = 17.39, 95%CI: 7.28-41.54, age ≥ 60 years(OR = 21.67, 95%CI: 8.27-56.80), males(OR = 17.95, 95%CI: 7.93-40.62), and females(OR = 20.95, 95%CI: 7.66-57.31); all P < 0.001. In the patient cohort of gastric cancer, the respective cutoff values showed that low serum folate levels were significantly associated with serosal invasion(OR = 2.54, 95%CI: 1.23-5.23), lymphatic invasion(OR = 2.23, 95%CI: 1.17-4.26), and liver metastasis(OR =6.67, 95%CI: 1.28-34.91) of gastric cancer(all P < 0.05). Serum folate level below 1.90 ng/mL was associated with poor patient survival(HR = 1.84, 95%CI: 1.04-3.27, P < 0.05) in univariate analysis.CONCLUSION: Lower serum folate levels were significantly associated with gastric cancer development and invasive phenotypes. The role of folate depletion in gastric cancer invasion warrants further study.

Statin use and the risk of colorectal cancer: A population-based case-control study

AIM: To investigate whether the use of statins is associated with colorectal cancer risk. METHODS: We conducted a population-based case-control study in Taiwan. Data were retrospectively collected from the Taiwan National Health Insurance Research Database. Cases consisted of all patients who were aged 50 years and older and had a first-time diagnosis of colorectal cancer between the period 2005 and 2008. The controls were matched to cases by age, sex, and index date. Adjusted odds ratios (ORs) and 95% confidence intervals (CIs) were estimated using multiple logistic regression. RESULTS: We examined 1156 colorectal cancer cases and 4624 controls. The unadjusted ORs for any statin prescription was 1.10 (95% CI = 0.94-1.30) and the adjusted OR was 1.09 (95% CI = 0.91-1.30). When statin use was categorized by cumulative dose, the adjusted ORs were 0.99 (95% CI = 0.78-1.27) for the group with cumulative statin use below 105 defined daily doses (DDDs); 1.07 (95% CI = 0.78-1.49) for the group with cumulative statin use between 106 and 298.66 DDDs; and 1.30 (95% CI = 0.96-1.75) for the group with cumulative statin use of 298.66 DDDs or more compared with nonusers. CONCLUSION: This study does not provide support for a protective effect of statins against colorectal cancer.

Temporal patterns of dengue epidemics:The case of recent outbreaks in Kaohsiung

Objective:To investigate whether major dengue outbreaks in the last two decades in Kaohsiung follow a precise temporal pattern.Methods:Government daily lab-confirmed dengue case data from three major dengue outbreaks occurring during the last two decades in Kaohsiung in2002,2014 and 2015,is utilized to compute the corresponding weekly cumulative percentage of total case numbers.We divide each of the three time series data into two periods to examine the corresponding weekly cumulative percentages of case numbers for each period.Pearson’s correlation coefficient was calculated to compare quantitatively the similarity between the temporal patterns of these three years.Results:Three cutoff points produce the most interesting comparisons and the most different outcomes.Pearson’s correlation coefficient indicates quantitative discrepancies in the similarity between temporal patterns of the three years when using different cutoff points.Conclusions:Temporal patterns in 2002 and 2014 are comparatively more similar in early stage.The 2015 outbreak started late in the year,but ended more like the outbreak in 2014,both with record-breaking number of cases.The retrospective analysis shows that the temporal dynamics of dengue outbreaks in Kaohsiung can strongly vary from one year to another,making it difficult to identify any common predictor.

Mobilization of Lead by Several Chelating Agents in Mice Injected with Lead

The relative abilities of several chelating agents to act as antagonists for acute and chronic lead poisoning have been examined in the mouse.The acute LD50 for lead acetate trihydrate was determined and found to be 135.3 mg Pb/kg for i. p. injection with a 95% confidence interval of 87.1 to 210.3 mg Pb/kg. The relative efficacy of chelating agents to reduce liver,kidney, spleen, bone and brain levels of lead was determined. The spleen levels were found to undergo little differences between the control and treated groups, but the liver, kidney, bone and brain levels showed significant differences in some cases. Of the compounds examind, meso-2, 3-dimercaptosuccinic acid （DMSA）and sodium 2,3-dimercaptopropane-1-sulfonate（DMPS） were as effective as disodium calcium ethylenediaminetetraacetate （Na2CaEDT A）. The resuits indicated that DMSA was a promising chelating agent and may be worthy of further investigation in the clinic.

Immunological Responses against Different Lineages of Influenza B Antigen in School Children during Two Consecutive Seasons

While Influenza B viruses currently circulating worldwide are of two distinct evolutionary hemagglutinin lineages, current trivalent inactivated influenza virus vaccines (TIV) contain only a single component. Single doses of TIV containing B antigen of B/Florida/4/2006 (Yamagata-like) or B/Brisbane/60/2008 (Victoria-like) were administered during 2008/2009 and 2009/2010 influenza seasons, respectively. The objective of this study was to evaluate the immunological response against different lineages of B antigens in school-aged children. A non-randomized sero-epidemiological study was conducted and the immunogenicity responses based on sero-protection rate and geometric mean titre ratio (GMTR) of hemagglutination inhibition (HI) antibodies were measured before and after immunization as well as post-influenza season. Our results suggested that school-aged children under the age of 9 years receiving TIV vaccination induced and retained higher level of sero-protection rate (66.7% and 69% for the 2008-09 and 2009-10 season, respectively) to the homologous lineage than the heterologous lineage post-vaccination (19.4% and 27.6% for the 2008-09 and 2009-10 season, respectively). The need for the quadrivalent TIV by including both lineages of influenza B viruses is recommended in this study, particularly for children under the age of 9 years.

Dengue outbreaks in Taiwan, 1998-2017: Importation, serotype and temporal pattern

Objective: To ascertain the role of imported cases and serotypes on dengue outbreaks in Taiwan which have been sporadic yet highly volatile during the past two decades, exhibiting record-breaking magnitude in recent years. Methods: Confirmed case and serotype data from Taiwan Centers for Disease Control during 1998-2017 were fully examined, with fitting of weekly and daily case data of each city/county to a mathematical model to pinpoint the waves of cases and their locations. Moreover, we quantify the timing of turning point and transmission potential of each wave and determine its circulating serotype, to ascertain any pattern or connection between the variations in circulating serotypes and the magnitude/transmissibility of outbreak. Results: While the number of imported case increased steadily during past two decades, the yearly number of indigenous cases fluctuated wildly. Moreover, while yearly percentages of serotypes for imported cases remains steady, that of indigenous cases does not exhibit any clear pattern. There was at least one wave of reported cases somewhere in Taiwan every year from 1998 to 2015, except in 2016-2017. The effective reproduction number R for all waves in all locations ranged from 1.14 to 2.87, with the exception of two Tainan waves, in 2010(3.95) and 2015(6.84). Four major outbreaks of over 2000 cases reveal circulation of one dominant serotype. Conclusions: Correlation between imported cases and indigenous outbreak prove to be difficult to ascertain, even with the availability of serotype data. However, although there had been occasional co-circulation of serotypes in one location, and for some years with different serotypes circulating in different locations, all major outbreaks of over 2 000 cases during the past two decades are due to circulation of mainly a single serotype, perhaps indicating greater transmission potential with one dominating serotype.

Influencing Factors and Improvement Strategies for Indoor Air Quality and Human Thermal Comfort in a Convenience Store

Indoor air quality has received increased attention. Surveying human thermal comfort and evaluating indoor airflow and ventilation can improve the integrity assessment of the indoor environment. In this study, indoor air quality measurements and spatial assessments were performed in a convenience store on a campus. The computational fluid dynamics model was used to simulate the indoor airflow and explore the spatial distribution of the CO2 concentration. The results showed the CO2 concentration easily surpassed the standard value during the weekdays and accumulated in short flows and dead zones. In the condition of no-building alterations, the preferred improvement strategy is to modify the air supply angle to 30°.

Effect of auricular acupuncture on oxygen consumption of boxing athletes

Boxing is an official sport at the 2008 Beijing Olympic Games and the fast development of world-class high strength training and sport science has made a significant impact on scientific training. Boxing needs high cardio-respiratory function, speed, muscle strength, and anaerobic and intensive physical demands including weight control covering the grading of athlete＇s body weight and balancing physical ability and health. Sport training is important even for talented athletes. Weight cycling is a term used to describe rapid weight loss following self food limitation and/or dehydration. Both gradual （seasonal） reduction cycles are used and rapid （weekly） weight by athletes,