Background Although the 2019 EULAR/ACR classification criteria for systemic lupus erythematosus (SLE) has required at least a positive anti-nuclear antibody (ANA) titer (≥ 1:80), it remains challenging for clinicians to identify patients with SLE. This study aimed to develop a machine learning (ML) approach to assist in the detection of SLE patients using genomic data and electronic health records. Methods Participants with a positive ANA (≥ 1:80) were enrolled from the Taiwan Precision Medicine Initiative cohort. The Taiwan Biobank version 2 array was used to detect single nucleotide polymorphism (SNP) data. Six ML models, Logistic Regression, Random Forest (RF), Support Vector Machine, Light Gradient Boosting Machine, Gradient Tree Boosting, and Extreme Gradient Boosting (XGB), were used to identify SLE patients. The importance of the clinical and genetic features was determined by Shapley Additive Explanation (SHAP) values. A logistic regression model was applied to identify genetic variations associated with SLE in the subset of patients with an ANA equal to or exceeding 1:640. Results A total of 946 SLE and 1,892 non-SLE controls were included in this analysis. Among the six ML models, RF and XGB demonstrated superior performance in the differentiation of SLE from non-SLE. The leading features in the SHAP diagram were anti-double strand DNA antibodies, ANA titers, AC4 ANA pattern, polygenic risk scores, complement levels, and SNPs. Additionally, in the subgroup with a high ANA titer (≥ 1:640), six SNPs positively associated with SLE and five SNPs negatively correlated with SLE were discovered. Conclusions ML approaches offer the potential to assist in diagnosing SLE and uncovering novel SNPs in a group of patients with autoimmunity.

Globalization has resulted in increases in air transportation demand and air passenger traffic. With the increases in air traffic, airports face challenges related to infrastructure, air services, and future development. Air traffic forecasting is essential to ensuring appropriate investment in airports. In this study, we combined fuzzy theory with support vector regression (SVR) to develop a fuzzy SVR (FSVR) model for forecasting international airport traffic. This model was used to predict the air traffic volumes at the world’s 10 busiest airports in terms of air traffic in 2018. The predictions were made for the period from August 2014 to December 2019. For fuzzy time series, the developed FSVR model can consider historical air traffic changes. The FSVR model can suitably divide air traffic changes into appropriate fuzzy sets, generate membership function values, and establish fuzzy relations to produce fuzzy interpolated values with minimal errors. Thus, in the prediction of continuous data, the fuzzy data with the smallest errors can be subjected to SVR to find the optimal hyperplane model with the minimum distance to the appropriate support vector sample points. The performance of the proposed model was compared with those of five other models. Of the compared models, the FSVR model exhibited the lowest mean absolute percentage error (MAPE), mean absolute error, and root mean square error for all types of traffic at all of the airports analyzed; all of the MAPE values were below 2.5. The FSVR model can predict future growth trends in air traffic, air passenger flows, aircraft flows, and logistics. An airport authority can use this model to analyze the existing operational facilities and service capacity, find bottlenecks in airport operations, and create a blueprint for future development. The findings revealed that implementing a hybrid modeling approach, specifically the FSVR model, can significantly enhance the performance of the SVR model. The FSVR model allows airlines to predict traffic growth patterns, identify viable new destinations, optimize their schedules or fleet, make accurate marketing decisions, and plan traffic effectively. The FSVR model can guide the timely construction of appropriate airport facilities with accurate predictions. Rapid, cost-effective, efficient, and balanced transportation planning enables the provision of fast, cost-effective, comfortable, safe, and convenient passenger and cargo services while ensuring the proper planning of the airport’s capacity for land-side transportation connections.

BACKGROUND:Rheumatoid arthritis (RA) and systemic lupus erythematous (SLE) are autoimmune rheumatic diseases that share a complex genetic background and common clinical features. This study's purpose was to construct machine learning (ML) models for the genomic prediction of RA and SLE.METHODS:A total of 2,094 patients with RA and 2,190 patients with SLE were enrolled from the Taichung Veterans General Hospital cohort of the Taiwan Precision Medicine Initiative. Genome-wide single nucleotide polymorphism (SNP) data were obtained using Taiwan Biobank version 2 array. The ML methods used were logistic regression (LR), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and extreme gradient boosting (XGB). SHapley Additive exPlanation (SHAP) values were calculated to clarify the contribution of each SNPs. Human leukocyte antigen (HLA) imputation was performed using the HLA Genotype Imputation with Attribute Bagging package.RESULTS:Compared with LR (area under the curve [AUC] = 0.8247), the RF approach (AUC = 0.9844), SVM (AUC = 0.9828), GTB (AUC = 0.9932), and XGB (AUC = 0.9919) exhibited significantly better prediction performance. The top 20 genes by feature importance and SHAP values included HLA class II alleles. We found that imputed HLA-DQA1*05:01, DQB1*0201 and DRB1*0301 were associated with SLE; HLA-DQA1*03:03, DQB1*0401, DRB1*0405 were more frequently observed in patients with RA.CONCLUSIONS:We established ML methods for genomic prediction of RA and SLE. Genetic variations at HLA-DQA1, HLA-DQB1, and HLA-DRB1 were crucial for differentiating RA from SLE. Future studies are required to verify our results and explore their mechanistic explanation.

Background: Classifying diseases into ICD codes has mainly relied on human reading a large amount of written materials, such as discharge diagnoses, chief complaints, medical history, and operation records as the basis for classification. Coding is both laborious and time consuming because a disease coder with professional abilities takes about 20 minutes per case in average. Therefore, an automatic code classification system can significantly reduce the human effort. Objectives: This paper aims at constructing a machine learning model for ICD-10 coding, where the model is to automatically determine the corresponding diagnosis codes solely based on free-text medical notes. Methods: In this paper, we apply Natural Language Processing (NLP) and Recurrent Neural Network (RNN) architecture to classify ICD-10 codes from natural language texts with supervised learning. Results: In the experiments on large hospital data, our predicting result can reach F1-score of 0.62 on ICD-10-CM code. Conclusion: The developed model can significantly reduce manpower in coding time compared with a professional coder.

With the coming of information age, the laboratory and the manufacture factory begins to import smart monitor system to enhance safety. The smart monitor system can save human costs. The information system can prevent unsafety event from happening. Smart Laboratory Administrator System was developed to cooperate with IoT (Internet of things) to prevent illegal invasion and achieve internal security. If unexpected events happen, it will work and switch on an alarm to prevent objects in the laboratory from being stolen. Hence, the Smart Laboratory Administrator System can save the human cost and enhance the security of laboratory.

Background: Pure-tone screening (PTS) is considered as the gold standard for hearing screening programs in school-age children. Mobile devices, such as mobile phones, have the potential for audiometric testing. Objective: This study aimed to demonstrate a new approach to rapidly screen hearing status and provide stratified test values, using a smartphone-based hearing screening app, for each screened ear of school-age children. Method: This was a prospective cohort study design. The proposed smartphone-based screening method and a standard sound-treated booth with PTS were used to assess 85 school-age children (170 ears). Sound-treated PTS involved applying 4 test tones to each tested ear: 500 Hz at 25 dB and 1000 Hz, 2000 Hz, and 4000 Hz at 20 dB. The results were classified as pass (normal hearing in the ear) or fail (possible hearing impairment). The proposed smartphone-based screening employs 20 stratified hearing scales. Thresholds were compared with those of pure-tone average (PTA). Results: A total of 85 subjects (170 ears), including 38 males and 47 females, aged between 11 and 12 years with a mean (SD) of 11 (0.5) years, participated in the trial. Both screening methods produced comparable pass and fail results (pass in 168 ears and fail in 2 ears). The smartphone-based screening detected moderate or worse hearing loss (average PTA>25 dB) accurately. Both the sensitivity and specificity of the smartphone-based screening method were calculated at 100%. Conclusions: The results of the proposed smartphone-based self-hearing test demonstrated high concordance with conventional PTS in a sound-treated booth. Our results suggested the potential use of the proposed smartphone-based hearing screening in a school-age population.

In this paper, we propose a new mechanism to improve the disadvantage of the security mechanism proposed by a scholar and then fulfill the demands of Internet of Things (IoT) to go through the decentralized environment access control functions. We also propose the date-constrained hierarchical key management scheme for mobile agents. With elliptic curve cryptosystems (ECCs) and discrete logarithms, the proposed scheme is flexible. Moreover, the duration of access for each security class is restricted with a certain authorized discrete time period. We demonstrate the mathematical derivation and arguments for our scheme and further conduct a numerical trial. The constructed scheme could meet security needs and be more space-efficient.

The mobile agent is functioning as an information exchanger with hosts. In order to reduce the communication time that the host sent to the members of a large system. This article proposes to use a function defined by Lagrange polynomial to compute decryption key. Each host will be given a decryption key to access the confidential document by inputting a secret key into an interpolation function which is generated from Lagrange interpolation. Since tasks are done by the mobile agent, the whole process will be performed within a short time period because there is no physical connection between the end devices. The information exchange occurs at the end hosts.

This research aims to conduct those college students who have not yet left their family before. At this phrase, students tend to form erroneous diet habits. These situations will lead to obesity and chronic diseases. The purpose of this research is to develop and design the smart Healthcare System for college students. Therefore, we hope to utilize the technology of information to make college students understand their dietary and whether they have enough physical activity or not. The objectives of this study is to develop an application. This application provide students a method to understand their habits both on the diet and the exercise. An interactive healthy diet evaluation and healthcare system is established in this research. With the convenience of mobile phones, the users can easily record the dietary contents, nutrient, and exercise process. According to the past dietary habits and exercise records, it also provides suggestions of nutrient allowance. The system, containing diet module and exercise module, can automatically offer suggestions according to the users’ basic information, including age, gender, favorite types of food, and amount of exercise. Students can inspect the nutrients they take to adjust their dietary and exercising habit. This can avoid the obesity which caused by the unbalanced long-term diet and the chronic diseases which might happen in the future. The mobile device application is applied at the system interface, the graphic interface, diagrams and images can effectively provide the users with various diets and exercise information. The users can use their own mobile devices whenever and wherever they need. They are not limited by the time and the space. Meanwhile, the system could record the amount of exercise by integrating with Google Map and rapidly inquire the past exercise records for the reference of self-inspection. In this research, we invite 80 students to conduct this experiment. We divide this experiment into two periods. For the first four weeks, students have to use hard paper to record the diet and exercise information. Students have to record at least three days within a week. We require two weekdays and one weekend and then we can assume the nutrients they have taken in a week. For the rest four weeks, every step is the same but the only difference is that students need to access the application of the mobile phones. The diet module analysis system will give proper suggestions and calculate the required nutrients for users, so that the users can change their dietary habits. Moreover, the system will recommend the users suitable types of food in the criteria. It will automatically remind the users of excessive or insufficient nutrient so as to give the users a way to select a suitable food for individuals and not to cause the body overwhelmed by the unbalanced nutrients. The exercise module will analyze the dietary records, suggesting appropriate running distance for proper exercise, and store the running data and distance records into the database. We invite 80 college students to conduct in this experiment. We can view the success rate via recording the three meals on the mobile phones. 60 students can fulfill the record of breakfast, which is 75 percent; 72 students can fulfill the record of lunch, which is 90 percent; 74 students can fulfill the record of dinner, which is 75.4 percent; as for the other snacks, 56 students can fulfill it, which is 70 percent. Compared with the first stage of recording on the hard paper, we have inspected that the success rate of lunch and dinner achieve 70 percent and even more. This system can store exercise data by integrating with Google Map and rapidly inquire the past exercise records for the reference of self-inspection. In this case, the users can understand whether the diet and exercise conform to the healthy demands of daily health records and further learn to select suitable food and improve the exercise habits. College students can bring the application conveniently and record the nutrients they take. This indeed can change the situation and the willingness. New generation needs to have a new tool and method to help them form good habits of dietary and exercise.

This paper improved the secure mechanism which existed some shortcomings. In order to accomplish the decentralized environment access control, it also proposed another new mechanism to achieve the requirements on the nonspecific internet. Besides, considering the security on storing and controlling and the use of administrative privileges of the lately popular medical system integration environment and electronic medical records clouds is necessary. With the new mechanism, the problems such as mobile security or acting calculation which derived from Medical System Environment and Electronic Medical Records could be solved. This new research achieves a better circumstance. Medical staff's responsibility can be allocated; the systems can be compatibly integrated; on the other hand, the patients' privacy of personal information can be strictly protected.

Vote by ballot is the feature in a democratic society and the process of decision-making, tending to achieve the philosophy of democratic politics by having the public who are eligible to vote for competent candidates or leaders. With the rapid development of technologies and network applications, electronization has been actively promoted globally during the social transformation period that the concept of electronic voting is further derived. The major advantages of electronic voting, comparing with traditional voting, lie in the mobility strength of electronic voting, reducing a large amount of election costs and enhancing the convenience for the public. Electronic voting allows voters completing voting on the Internet that not only are climate and location restrictions overcome, but the voter turnout is also increased and the voting time is reduced for the public. With the development in the past three decades, electronic voting presents outstanding performance theoretically and practically. Nevertheless, it is regrettable that electronic voting schemes still cannot be completely open because of lures by money and threats. People to lure by money and threats would confirm the voters following their instructions through various methods that more factors would appear on election results, affecting the quality and fairness of the election. In this study, this project aims to design an electronic voting scheme which could actually defend voters’ free will so that lure of money and threats would fail. Furthermore, an electronic voting system based on Elliptic Curve Cryptography is proposed to ensure the efficiency and security, and Ring Signature and Signcryption are applied to reducing the computing costs. Moreover, this project also focuses on applying voting system to mobile devices. As the system efficiency and security are emphasized, voters do not need to participate in the election, but simply complete voting with smart phones, iPads, and computers. The votes would be automatically calculated and verified the results that the ballots are not necessarily printed, the printing of election mails is reduced, and manual handling is canceled. Such a method would effectively reduce voting costs and enhance the economic efficiency.

Recently, countries worldwide have actively developed approaches to improve the quality of healthcare and reduce healthcare costs. One of these approaches involves replacing human labor with wireless information transmission. On the basis of the wireless sensor networks employed for medical monitoring in hospitals and healthcare institutions, this paper proposes a user authentication scheme and data transmission mechanism that facilitates security and privacy protection, enable medical personnel to instantly monitor the health conditions of care receivers, and provide care receivers with prompt and comprehensive medical care. Using both smart cards and passwords, our scheme grants only legal medical personnel access to patient information such as body temperature, heart rate, and blood pressure. In addition, a secure cryptosystem was applied for establishing a data transmission mechanism. Furthermore, this scheme can resist common attacks, such as impersonation, replay, online or offline password guessing, and stolen-verifier attacks.

Purpose - Owing to the wave of consumers concern about food quality, the organic food market has grown rapidly. However, how organic food promotions outweigh the negative impacts of high prices has become a pressing issue scholars need to discuss. Hence, with the value perspective as the basis, the purpose of this paper is to attempt to understand whether or not organic food consumers have preferences for specific promotional programs as opposed to other promotional programs.Design/methodology/approach - The two-stage study design was adopted to explore these issues. In the first stage, 225 copies of promotional program documents were collected, and middle-ranking and high-ranking supervisors from seven organic food distributors were interviewed. According to the value perspective, the promotional programs were divided into four types: discount category, member category, free giveaway category, and limited time offer category, which were used to develop the questionnaire questions. In the second stage, 1,017 copies of valid questionnaires were recovered.Findings - The logistic regression analysis was adopted to discuss the impact of the various promotional program actions on consumers' choices. The empirical results indicate that the consumers preferred the programs in the discount category and the free giveaway category, while the programs in the member category and limited time offer category reduced the purchase intention.Originality/value - The stringent qualitative and quantitative design in this study shall serve as a reference for follow-up research. The important implications of the operators' promotion practices are covered in the discussion.

Muscle strength and muscle oxygen saturation are two typical indicators for the evaluation of exercise effects in rehabilitation and sport medicine. The aim of this study was to compare the effects of low-intensity exercise training on muscle strength and muscle oxygen saturation monitored by near infrared spectroscopy (NIRS) in older adults. Eighteen healthy community-dwelling older adults, age mean (SD), 78.7 (7.3) years, were recruited. Ten subjects (exercise group) participated 6-week training program for lower-extremity, and the others were control. The training program was composed of 15-minute exercise course using three machines for lowerextremities training three times a week for six weeks. The intensity of machines were adjusted to 50% of one repetition maximum for each participants respectively. Heart rate, blood pressure, blood oxygen, muscle strength and muscle oxygen saturation, were measured before and after the 15-minute course in week zero (Week 0, before the 6-week training program) and 7th week (Week 7, after the training program). The Student’s t-test was used to compare the difference of these variables between groups. The effective fall in quadriceps muscle oxygen saturation, Deff, is defined as the decrease in oxygen saturation from quiet baseline (BL) to the end of one 15-minute course (Post-exercise, PE). After 6-week training program, Deff did not change in the exercise group, while it decreased significantly in control group. Quadriceps muscle strength did not change after 6-week program in the exercise group, but decreased about 6% in the control group (not significant). Heart rate, blood pressure and blood oxygen were unaffected in the exercise group and the control group. The ambient temperatures were 25.8 .. and 19.9 .. for Week 0 and Week 7 respectively (p<0.0001). The training program counterbalance the muscular function decline due to seasonal variation from the end of autumn to winter for subjects participating the exercise program, while the function declined in control group. We suggest the non-invasive measurement of muscle oxygen could be used to assess the effect of physical activity program in community.

Flexibility testing is one of the most important fitness assessments. It is generally evaluated by measuring the range of motion (RoM) of body segments around a joint center. This study presents a novel assessment of flexibility in the microcirculatory aspect. Eighteen college students were recruited for the flexibility assessment. The flexibility of the leg was defined according to the angle of active ankle dorsiflexion measured by goniometry. Six legs were excluded, and the remaining thirty legs were categorized into two groups, group H (n = 15 with higher flexibility) and group L (n = 15 with lower flexibility), according to their RoM. The microcirculatory signals of the gastrocnemius muscle on the belly were monitored by using Laser-Doppler Flowmetry (LDF) with a noninvasive skin probe. Three indices of nonpulsatile component (DC), pulsatile component (AC) and perfusion pulsatility (PP) were defined from the LDF signals after signal processing. The results revealed that both the DC and AC values of the group H that demonstrated higher stability underwent muscle stretching. In contrast, these indices of group L had interferences and became unstable during muscle stretching. The PP value of group H was a little higher than that of group L. These primary findings help us to understand the microcirculatory physiology of flexibility, and warrant further investigations for use of non-invasive LDF techniques in the assessment of flexibility.

Observing the pattern changes of inpatient fall and validating the Fall Prevention Tool Kit (FPTK) are essential for developing fall prevention strategies. However, the work requires the collection, calculation, and comparison of large amount of data. The information is often scattered in diverse information systems and lack of integration, which makes the work difficult and often neglected. This study demonstrates the development of an Interactive Data Repository System (IDRS) and uses it in the analysis of the pattern changes of inpatient fall within the institute, and validates efficiency of the FPTK across time. This study collected the incident data of year 2011 and compared it with the previous analysis in 2001. The result shows that reasons for patient fall had turned from physical disability to impaired conscious or cognition. The scoring result may be too sensitive in identifying patient falls. Patients with high scores needed to reinforce in functional strength.

A lot of manufacturers tend to enhance the management efficacy and reduce the management costs by investing large resources in the research and development of RFID. For petrochemical industry, an effective, reliable, and secure patrol management system is primary. Nevertheless, traditional patrol management focuses on labor patrol that the field staff master in the corrosion, leakage, and pipe aging of production equipment. Although equipment inspection and patrol items are scheduled every day, some problems still need to be overcome. After completing traditional patrol tasks, extra time and manpower are required for organizing the patrol records and filling them into electronic document. In the process, it is likely to key in wrong data because of the numerous patrol items. Apparently, without systematic management, supervisors and shift leaders can hardly find out data errors and analyze the abundant data for complete risk evaluation and process security improvement. An RFID-based patrol management system suitable for petrochemical industry is proposed in this study. The system corresponds to the field environment requirements and regulations for petrochemical plants, integrates operation procedure and information procedure, and evaluates and includes various dimensions and variables through interviews and technological analyses to enhance the process security. Active processing equipment monitoring could enhance the preventive maintenance efficiency and promote the production capacity and industrial competitiveness.

Hospital selection is a complicated decision-making process. Although patients have expressed greater desire to participate in decision-makings of their healthcare, it can be problematic for them to accumulate large amount of information and using it for making an optimal choice in hospital selection. The aim of this research is to develop a decision engine for hospital selection (DEHS) to support patients while accessing healthcare resources. DEHS applied the analytic hierarchy process and the geographic information system to aggregate different decision factors and spatial information. The results were evaluated through investigating the consistency of the preferences that users inputted, the degree that the results match patient choices, the satisfactions of users, and the helpfulness of the results. Data were collected for 3 months. One hundred and four users visited DEHS and 85.5 % of them used DEHS more than once. Recommendations of the institutes (36 %) was ranked as the primary decision factor that most users concerned. Sixty-seven percent of the sessions searched for hospitals and 33 % for clinics. Eighty-eight percent of the results matched the choices of patients. Eighty-three percent of the users agreed that the suggested results were satisfactory, and 70 % agreed that the information were helpful. The DEHS provides the patients with simple measurements and individualized list of suggested medical institutes, and allows them to make decisions based on credible information and consults the experiences of others at the same time. The suggested results were considered satisfactory and helpful.