A medical Chatbot using machine learning and natural language understanding

Multimedia Tools and Applications - For people with busy schedules, travelling to and from a hospital for treatment is considerably time consuming, which leads them to ignore their health problems....     

Software Optimization in Ultrasound Imaging Technique Using Improved Deep Belief Learning Network on the Internet of Medical Things Platform

Wireless Personal Communications - The Internet of Medical Things (IoMT) is the array of medical instruments and related technologies that link Information Technology (IT) systems in...     

Automated prediction system of household energy consumption in cities using web crawler and optimized artificial intelligence

The supply of electrical energy is critical to convenient and comfortable living. However, people consume a large amount of energy, contributing to an energy crisis and global warming, and damaging some ecological cycles. Residential electricity consumption has greater elasticity than industrial and business consumption; it therefore has high energy-saving potential. This work establishes an automated platform, which provides information about residential electricity consumption in each city in Taiwan. Machine learning was used to forecast future residential electricity demand. A nature-inspired optimization method was applied to enhance the accuracy of the best machine learner, yielding an even better hybrid ensemble model. Performance measures indicate that the resulting model is accurate and provides effective information for reference. An automatic web-based system based on the model was combined with a web crawler and scheduled to run automatically to provide information on monthly residential electricity consumption in each county and city. By providing energy consumption information across the country, power providers and government can discuss policy and set different goals for energy use. The results of this study can facilitate the early implementation of energy-saving and carbon emission-reducing in cities and aid utility companies in establishing energy conservation guidelines.     

仿真虚拟实训中心建设在药学高等职业教育中的应用

在当前信息技术快速发展的社会,虚拟仿真实训开始在高等职业教育教学中广泛应用,使用虚拟仿真实训技术能够有效的解决当前高等职业教育实践教学中存在的一些突出问题,能对传统的教育教学模式进行有效的补充。本文以仿真虚拟实训中心建设为切入点,就其建设及其在高等职业教育药学专业中的应用进行分析,以期使虚拟仿真实训中心在提高实践教学效果方面发挥重要作用。     

锌铝水滑石的制备及其在制革少铬鞣中的应用

通过共沉淀法制备了锌铝水滑石(ZnAl-LDH),采用XRD、FTIR、SEM对其结构进行了表征.将其配合用量为皮质量2％的铬粉(记为2％铬粉)应用于制革鞣制工艺中.考察了ZnAl-LDH制备时的金属源物质的量比、陈化时间对鞣制坯革收缩温度、鞣后废液中的Cr2O3质量浓度的影响.结果表明,ZnAl-LDH是尺寸在100～400 nm之间的片状材料.当n〔(Zn(NO3)2?6H2O)〕:n〔Al(NO3)3?9H2O〕=2.0:1.0,陈化时间为6 h时,制备的ZnAl-LDH-4具有优异的性能.与单独使用2％铬粉鞣制坯革相比,ZnAl-LDH-4(用量为皮质量的4％)配合2％铬粉鞣制坯革收缩温度由75℃提高到94℃,废液中的Cr2O3质量浓度由99.58 mg/L降低至46.98 mg/L,且加入ZnAl-LDH-4鞣制后,鞣后废液化学需氧量和生物需氧量均降低.     

Spinel CoFe2O4 /carbon nanotube composites as efficient bifunctional electrocatalysts for oxygen reduction and oxygen evolution reaction

In the development of fuel cells, it is the key to large-scale commercialization of fuel cells to rationally design and synthesize efficient and non-noble metals-based bifunctional electrocatalysts for oxygen reduction reaction (ORR) and oxygen evolution reaction (OER). In this paper, spinel CoFe₂O₄/carbon nanotube composites (CoFe₂O₄/CNTs/FA) were synthesized by solvothermal and calcination method. XRD, TEM, XPS and BET characterizations indicate that the addition of complexing agent fumaric acid can improve the crystal growth kinetics and morphology of CoFe₂O₄/CNTs nanohybirds. The as-synthesized CoFe₂O₄/CNTs/FA pyrolyzed at 500 °C have an outstanding bifunctional catalytic activity for ORR and OER with the potential of 1.62V (vs. RHE) at a current density of 10 mA/cm² and half-wave potential E_1/2 = 0.808V (vs. RHE) in alkaline electrolyte, respectively. It is obviously better than unloaded CoFe₂O₄ nanoparticles and commercial CNTs. CoFe₂O₄/CNTs/FA also exhibit better methanol tolerance ability and durability than commercial Pt/C and RuO₂ catalyst. This investigation broadens an idea of simple compounding of spinel with carbon-based materials to improve electrochemical properties.     

Preparation and antifouling performance of thin inorganic ultrafiltration membrane via assisted sol-gel method with different composition of dual additives

A novel TiO₂ thin film was prepared on the ceramic hollow fiber by the sol-gel method using poly(vinylpyrrolidone) (PVP) and polyvinyl alcohol (PVA) as additives. SEM images verified the formation of TiO₂ layer with various thickness using different composition of titania sols. The effect of the PVP and PVA contents on the TiO₂ sol properties, the separation and the antifouling performance of the ultrafiltration membranes were investigated thoroughly. When the contents of PVP and PVA were 1.0 wt% and 0.8 wt%, respectively, the resultant membrane showed a thickness of 0.55 μm with a pure water flux of 255 L m^?2 h^?1. In addition, the adherent foulant bovine serum albumin was applied to evaluate the antifouling performance. During the three fouling-recovery cycles, the flux recovery ratio and the flux decay ratio maintained about 99% and 30%. The BSA flux and rejection were still 169 L m^?2 h^?1 and 96.9% after the cycles, indicating a superior antifouling property.