365 research outputs found
Emerging Advancement of Data Science in the Healthcare Informatics
No full textThe healthcare domain is experiencing a massive transition, driven by the threefold target of increased efficiency, reduced costs and positive results for patients. The lack of clinical experience impact can largely be due to inadequate statistical model effectiveness, difficulties understanding dynamic model forecasts, and lack of evidence from prospective clinical trials that have a strong benefit over the standard of treatment. In this article, the promise of personalized medicine's state-of-the-art data science methods, discussing open barriers, and Highlight paths that might in the future help to solve them. We should anticipate many shifts in future medical informatics science in view of the fluid existence of many of the driving factors behind advancement in knowledge management methods and their technology, developments in medicine and health care, and the constantly shifting demands, requirements and aspirations of human populations. This chapter gives brief explanation for relevance of the applications of predictive analytics strategies and importance of data science in healthcare.</p
A Value of Data Science in the Medical Informatics: An Overview
No full textThe use of data science and predictive modelling for real-time clinical decision making is increasingly recognized. The initial step in the path towards the adoption of real-time prediction and forecast is the creation and evaluation of predictive models for clinical practice. Training in medical informatics is not only necessary for medical students but also for all medical personnel at all technical levels of education. A critical move required for the learning and application of clinical medicine is to incorporate medical informatics into the broad scope of medical informatics. Current major fields of research can be categorized according to the organization, implementation, assessment, representation, and interpretation of medical information. We should expect many changes in medical informatics, because of many of the driving forces behind advancement in information management methods and their innovations, developments in medicine and health care, and the constantly evolving needs, requirements and aspirations of human societies. Data science and predictive analytics offer distinct methodologies for tapping vast data sets of medical knowledge from intelligence. These approaches have many possibilities, such as identifying patterns, forecasting outcomes, and optimizing algorithms better. But medical data collection and management often faces few problems, such as data size, data consistency, durability and data completeness. This research offers an extensive overview of medical data processing, predictive analytics and data science in order to contribute to the area of medical informatics and data science. It offers explanations of basic principles using data science in the evolving field of medical informatics. Also the research includes review of benefits, applications and future of data science in healthcare.</p
Potential and Adoption of Data Science in the Healthcare Analytics
No full textThe creation and validation of clinical practice predictive models is just the initial step in the path towards mainstream adoption of predictions for real-time point-of-care. Adoption of healthcare analytics can occur at diverse levels, including medical error tracking and avoidance, data integration, predictive analysis and personalized modelling. Although substantial advancement and progress has been made from the perspective of data science and study, challenges and opportunities remain. Current main fields of study can be categorized according to the organisation, introduction, and assessment of health information systems, patient information representation, and analysis and interpretation of underlying signals and data. We should anticipate many shifts in future medical informatics science in view of the fluid existence of many of the driving factors behind advancement in knowledge management methods and their technology, developments in medicine and health care, and the constantly shifting demands, requirements and aspirations of human populations. This chapter will explain the relevance of the application of predictive analytics strategies focused on data science in healthcare. By way of intelligent process analysis and medical data mining, the device would be able to derive real time valuable information that aids in decision making and medical tracking.</p
Eminent Role of Machine Learning in the Healthcare Data Management
No full textThe large quantities of data that can be produced in the medical sector. Each healthcare institution has its own patient records that include important details. When correctly evaluated, the healthcare domain will produce value from this data. A critical step necessary for the learning and application of clinical medicine is to bring medical informatics into the broad scope of medical education. Current main research areas can be categorized according to the organisation, introduction, and assessment of health information systems, the representation of medical expertise, and the study and interpretation of underlying signals and evidence. Machine learning has become really popular in the last few decades, and different methods of machine learning have been developed. It concentrates on the analyzing, developing, designing and implementing of techniques. The algorithms for machine learning use a well-defined learning method that best fits the purpose of the medical data analytics. Simple principles of the healthcare sector and machine learning will be defined in this study. The chapter shows how data analytics and machine learning can assist in the healthcare process, also posing certain obstacles, possibilities that need to be explored in order to achieve successful analytics in healthcare diagnosis.</p
Data Science in Medical Informatics: Challenges and Opportunities
No full textThe healthcare system is undergoing a significant transition, necessitated by the triple goal of improving efficiency, lower costs and improving outcomes. Healthcare analytics may be implemented at different levels, including monitoring and avoiding medical errors, data integration, predictive analysis and personalized modelling. Although substantial advancement and progress has been made from the perspective of data science and study, challenges and opportunities remain. Current major fields of study can be categorized according to the organisation, implementation and assessment of health information systems, the representation of medical information and the analysis and interpretation of underlying signals and data. We can anticipate many changes in future medical informatics science, considering the fluid existence of many of the driving forces behind innovation in information processing methods and their technology, advancement in medicine and health care, and the rapidly evolving needs, requirements and desires of human societies. This chapter consists of opportunities and challenges of data science in healthcare information analysis. Also data analytics stages, future and its technologies are briefly discussed.</p
Heterogeneity in behavioural response to pricing policies in the transition from motorcycles to private cars in motorcycle-based societies
No full textPricing instruments are widely seen as an effective tool for reducing the travel demand for private vehicles. In contrast to developed countries, the design of pricing policies in certain developing countries is more challenging, owing to the mixed use of private cars and motorcycles. This study argues for the existence of a transitional group of motorcycle users who will switch to being car users. An investigation of the behavioural responses to a pricing policy from private car users and motorcycle users is implemented in Ho Chi Minh City, Vietnam. A propensity score-matching technique is used to identify the transitional group. The results regarding the mode choice models for various pricing policies show similar responses between the transitional motorcycle users and car users. Such characteristics of the transitional group imply that ignorance of travellers' heterogeneity may cause significant bias, especially when modelling pricing policies.This research was financed by the Special Research Fund of Hasselt University.
Financial support in data collection: Ho Chi Minh City Institute for Development Studies (HIDS)
Author contribution: The authors confirm contribution to the paper as follows: study concept and design: Hoang Thuy Linh, Nguyen Hoang Tung, Vu Anh Tuan, Muhammad Adnan, and Tom Bellemans; data preparation, analysis, and interpretation of results: Hoang Thuy Linh; draft manuscript preparation: Hoang Thuy Linh, Nguyen Hoang Tung, and Muhammad Adnan. All authors reviewed the results and approved the final version of the manuscript
A Review of Applications of Machine Learning for Emissions Estimation in Diesel Engines
No full textPublisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.There has been an increasing demand to reduce the emissions of diesel engines, especially in maritime applications. Moreover, emission regulations are becoming stricter every year. This has led to an urge for more complex engine control systems with more accurate emissions estimators included. Machine learning methods have been long adopted to create models with high complexity to estimate the engine’s emissions and to rely less on conventional physical measurement devices. This paper presents a brief review of the development of engine emissions estimation using machine learning methods over the last 20 years. The review will however mainly focus on emissions prediction from engine in-cylinder pressure and engine functional vibration signal.Peer reviewe
FIGURE 1 in A new snake of the genus Dendrelaphis Boulenger, 1890 (Squamata: Colubridae) from the coastal area of southern Vietnam
No full textFIGURE 1. Map showing the distribution of Dendrelaphis binhi sp. nov. (triangles) and D. subocularis (dots) in Vietnam. 1, Chi Linh, Hai Duong Prov.; 2, Chu Lai, Quang Nam Prov.; 3. Khanh Hoa Prov.; 4, D'ran, Lam Dong Prov.; 5, Phan Rang, Ninh Thuan Prov.; 6, Thuan Nam, Ninh Thuan Prov.; 7, Tuy Phong, Binh Thuan Prov.; 8. Binh Chau, Ba Ria—Vung Tau Prov.; 9, Tan Bien, Tay Ninh Prov.Published as part of Nguyen, Sang Ngoc, Nguyen, Vu Dang Hoang, Le, Manh Van, Nguyen, Luan Thanh, Vo, Thi-Dieu-Hien, Vo, Ba Dinh, Che, Jing & Murphy, Robert W., 2023, A new snake of the genus Dendrelaphis Boulenger, 1890 (Squamata: Colubridae) from the coastal area of southern Vietnam, pp. 130-144 in Zootaxa 5318 (1) on page 131, DOI: 10.11646/zootaxa.5318.1.6, http://zenodo.org/record/815833
A review of mathematical methods for flexible robot dynamics modeling and simulation
No full textIn recent decades, lots of robots are designed and produced all over the world because of their important applications. Nowadays, using the robot is more and more popular in many different fields. In practice, the modeling and control of most of the robots are performed with an important assumption that all links of a robot are rigid bodies. This is to simplify the modeling, analysis, and control for a robot. The elastic deformation of a link always exists during a robot’s operation. This elastic deformation of a flexible robot has significant effects on several characterizations and specifications of the robot such as the robot strength, the accuracy of the robot motion, the robot control, etc. In the literature, there have been many studies addressing the dynamics modeling and control of flexible robots. This paper presents an overview of the mathematical methods which have been used for the kinematic and dynamic modeling of the flexible manipulators
Climate change adaptation and sustainable agriculture : the case of saltwater intrusion and rice production in central coastal region of Vietnam
No full text- …
