1,723,287 research outputs found
Embracing Industrial 4.0 : The Role of Robotics and AI
No full textIndustry 4.0 is transforming the future of industry and manufacturing towards smart factories with increased digitisation, automation and integrated control systems. The development of robotics, AI and Internet of Things (IoT) has played an important role in supporting this major development. This talk will highlight the technical advances that underpin Industry 4.0 and use the medtech sector as the exemplar for outlining the opportunities as well as the challenges faced by academia and commercial sectors. The talk will also cover the successes, challenges, and the road ahead for medical robotics in spearheading evolution in precision medicine and personalized healthcare. We will look back through the last 25 years at how surgical robotics has evolved to a major area of innovation and development. With improved safety, efficacy and reduced costs, robotic platforms will soon approach a tipping point, moving beyond early adopters to become part of the mainstream surgical practice. These platforms will also drive the future of precision surgery, with a greater focus on early intervention and quality of life after treatment. We also project forward, on how this relatively young yet rapidly expanding field may reshape the future of medicine, as well as the associated technical, commercial, regulatory, and economic challenges that need to be overcome. The talk will conclude with the vision for creating the future medtec eco-system by leveraging the increasing adoption of Industry 4.0 for the development of safe, effective, and accessible medical device platforms that will benefit the population at large
Time series forecasting based on deep extreme learning machine
Get PDFMulti-layer Artificial Neural Networks (ANN) has caught widespread attention as a new method for time series forecasting due to the ability of approximating any nonlinear function. In this paper, a new local time series prediction model is established with the nearest neighbor domain theory, in which the hybrid Euclidean distance is used as the similarity measurement between two sets of time series. In order to improve the efficiency, prediction performance, as well as the ability of real-time updating of the model, in this paper, the recombination samples of the model is derived by Deep Extreme Learning Machine (DELM). The experiments show that local prediction model gets accurate results in one-step and multi-step forecasting, and the model has good generalization performance through the test on the five data sets selected from Time Series Database Library (TSDL).Accepted Author ManuscriptTransport Engineering and Logistic
Exploring the potential of desalination and aquaponics in the integrated management of arid river basins: the case of the Nile River basin
No full textA new species of Protopsyllidiidae (Hemiptera, Sternorrhyncha) from the Middle Jurassic of China
No full textYang, Guang, Yao, Yunzhi, Ren, Dong (2012): A new species of Protopsyllidiidae (Hemiptera, Sternorrhyncha) from the Middle Jurassic of China. Zootaxa 3274: 36-42, DOI: 10.5281/zenodo.21465
Antimicrobial inks: the anti-infective applications of bioprinted bacterial polysaccharides
No full textBioprinting is a rapidly emerging technology with the potential to transform the biomedical sector. Here, we discuss how a range of bacterial polysaccharides with antibiofilm and antibacterial activity could be used to augment current bioink formulations to improve their biocompatibility and tackle the spread of antibiotic-resistant infections.</p
Optimized design of self-powered SSHI interface circuit for enhanced vibration energy harvesting
No full textVibrational energy in ambient environment can be transformed into electrical power through piezoelectric energy harvesters, and using synchronized switch harvesting on inductor (SSHI) techniques can significantly improve energy extraction efficiency. To enhance energy harvesting efficiency, this study proposes an efficient self-powered parallel SSHI (ESP-PSSHI) interface circuit. It enhances the passive peak detection switch, simplifies the circuit topology, reduces switching delay, and minimizes the "second inversion", contributing to increased energy harvesting efficiency. To improve the impedance-matching characteristics of the circuit, the proposed circuit is combined with a DC-DC converter module and finally, a stable electrical output is achieved. The performance of the ESP-PSSHI circuit in power generation is analyzed through simulation and subsequently verified via experimentation. Experiments show that the maximum output power of the ESP-PSSHI circuit is 2.42 and 1.16 times higher than the output power of the standard energy harvesting (SEH) circuit and self-powered parallel SSHI (SP-PSSHI) circuit, respectively. Through capacitor charging experiments, it is concluded that the output power of the optimized ESP-PSSHI circuit is 1.5 times the output power of the LTC3588-1 circuit
- …
