Elearning is the implementation of information technology in learning. Elearning was used in courses in Introduction to Business and Management, Business Process Management and Ebusiness. This study aims to use the Technology Acceptance model (TAM) to measure the level of user satisfaction. TAM method is used to determine the relationship between content, accuracy, format, ease of use, timelines, organizational support, user attitudes towards the information system (user attitude towards information). system) and perceived attitude of top management on the level of satisfaction of using e-learning on learning business courses and management at the Faculty of Computer Science, Duta Bangsa University Surakarta. This research is a descriptive study using the modified End User Computing Satisfaction (EUCS) approach method. The results of the evaluation study show that the 5 variables (content), the level of accuracy of the system, format, easy of use, and timeliness significantly influence user satisfaction. While organizational support variables have a significant effect on user satifaction but variable usser attitude toward information system and perceived attitude of top management has an effect but not significant to the support organization. Key words : elearning, user satisfaction, technology acceptance model, end user computing satisfaction.

The mapping of students will help the selection of student specialization in the research field. The purpose of this research is to develop and develop a decision support system to map and provide direction in the suitability of specialization in the field of computer / information technology to students. Development of a decision sThe mapping of students will help the selection of student specialization in the research field. The purpose of this research is to develop and develop a decision support system to map and provide direction in the suitability of specialization in the field of computer / information technology to students. Development of a decision support system design to map computer students with regard to the types of specialization in IT and Computing specialization. The specialization of students is divided into 8 specializations. The specialization is then correlated with indicators namely interests, grade of subjects, learning styles, multiples intelligences and cognitive styles. The leaning styles according to Memeletics Learning Styles Inventory consist 7 types namely : Visual, Aural, Verbal, Physical, Logical, Social and Solitary. The Multiple Intelligences according to Gardner's Multiple Intelligences Scale consist 8 types namely : Linguistics Intelligence, Logical Mathematics Intelligence, Visual Spatial Intelligence, Bodily Kinesthetics Intelligence, Musical Intelligence, Interpersonal Intelligence, Intrapersonal Intelligence and Naturalist Intelligence. The Cognitive Styles according to Martin Cognitive Styles Inventory consist 5 types namely: Systematic Style, Intuitive Style, Integrated Style, Undifferentiated Style and Split Style.upport system design to map computer students with regard to the types of specialization in IT and Computing specialization. The specialization of students is divided into 8 specializations. The specialization is then correlated with indicators namely interests, grade of subjects, learning styles, multiples intelligences and cognitive styles. The leaning styles according to Memeletics Learning Styles Inventory consist 7 types namely : Visual, Aural, Verbal, Physical, Logical, Social and Solitary. The Multiple Intelligences according to Gardner.'s Multiple Intelligences Scale consist 8 types namely : Linguistics Intelligence, Logical Mathematics Intelligence, Visual Spatial Intelligence, Bodily Kinesthetics Intelligence, Musical Intelligence, Interpersonal Intelligence, Intrapersonal Intelligence and Naturalist Intelligence. The Cognitive Styles according to Martin Cognitive Styles Inventory consist 5 types namely: Systematic Style, Intuitive Style, Integrated Style, Undifferentiated Style and Split Style.

Heart disease and stroke are the main contributions to health disorder. Two factors influence the susceptibility of the disease, namely clinical risk factors and non-clinical factors. This study aims to analyze the effect of non-clinical risk factors on the susceptibility to heart disease and stroke. The non-clinical risk factors are stress management, age, obesity, genetics, smoking, gender, lifestyle (nutrition), lifestyle (timing rest), and physical activity. Analysis of the influence of non-clinical risk factors on susceptibility using statistical methods, namely descriptive statistics, normalization tests with the Kolmogorov-Smirnov test, validity tests, reliability tests, and correlation tests. The descriptive statistical tests show that the risk factors for stress management, obesity, and smoking have a more significant influence than others. While Gender and physical activity have more negligible effect than others. Testing with one sample Kolmogorov-Smirnov Test shows that the data is normally distributed. Validity testing produces 100% valid data. The reliability test using Cronbach's alpha of 9 non-clinical risk factor items resulted in a value of 0.684, which means reliable. Correlation test between 9 items of non-clinical risk factor shows significant between items.

Penyakit jantung merupakan salah satu penyebab kematian baik di dunia maupun Indonesia. Perhatian awal dari penyakit jantung akan memudahkan pencegahan dan penyembuhanya. Tujuan penelitian ini adalah melakukan analisis komapratif  model klasifikasi dengan berbagai algoritma machine learning untuk kerentanan penyakit jantung. Dataset diambil dari UCI machine Learning Resipatory dengan 300 data training dan 100 data testing. Parameter klasifikasi terdiri dari age, sex, systolic blood pressure, cholesterol, thalach, oldpeak dan slope, serta labelnya cardio. Model klasifikasi dibangun dengan algoritma Naïve Bayes, K-Nearest Neighbor (KNN), Decision Tree, random Forest, Backpropagation, Logistic Regression dan Support Vector machine (SVM). Hasil model klasifikasi dari pengukuran accuracy didapatkan Naïve Bayes (79,00%), KNN (63,00%), Decision Tree (66,00%), Random Forest (77,00%), Backpropagation (80,00%), Logistic Regression (81,00%) dan SVM (80,00%). Dari analisis komparatif pegukuran parameter accuracy, precision, recall dan F1 score maka model klasifikasi dengan algoritma Logistic Regression dan backpropagation menghasilkan performa terbaik.

The objectives of this research is to implementation wavelet neuro fuzzy method to predict water level of Bengawan Solo river. The wavelet neuro fuzzy method is a model combination between discrete wavelet transformation, Artificial Neural Network (ANN) and fuzzy logic. Wavelet Neuro fuzzy modeling aims to reduce the weaknesses of each system, and combine existing advantages of each system, so the predicted result has a very small error value. Predicted when the flood is important because the predicted result can provide early warning information to the community around the river when the arrival of floods so as to reduce the risk of disaster and prepare for emergency response action. The data used in this research are high level of water level data obtained from AWLR Serenan post. The results of the wavelet neuro fuzzy method show the Mean Square error (MSE) forecast of 0.0613.