deep generative models, de novo molecule generation
| INTRODUCTIONDe novo design of new molecules and analysis of their structure and properties is an important issue in computational molecular science. In the last few years, new approaches based on artificial intelligence (AI), especially deep learning models, have *These authors contributed equally to this study.
The contactless estimation of the weight of a container and the amount of its content manipulated by a person are key pre-requisites for safe human-to-robot handovers. However, opaqueness and transparencies of the container and the content, and variability of materials, shapes, and sizes, make this problem challenging. In this paper, we present a range of methods and an open framework to benchmark acoustic and visual perception for the estimation of the capacity of a container, and the type, mass, and amount of its content. The framework includes a dataset, specific tasks and performance measures. We conduct a fair and in-depth comparative analysis of methods that used this framework and audio-only or vision-only baselines designed from related works. Based on this analysis, we can conclude that audioonly and audio-visual classifiers are suitable for the estimation of the type and amount of the content using different types of convolutional neural networks, combined with either recurrent neural networks or a majority voting strategy, whereas computer vision methods are suitable to determine the capacity of the container using regression and geometric approaches. Classifying the content type and level using only audio achieves a weighted average F1-score up to 81% and 97%, respectively. Estimating the container capacity with vision-only approaches and filling mass with audio-visual approaches, multi-stage algorithms reaches up to 65% weighted average capacity and mass scores. These results show that there is still room of improvement for the design of future methods that will be ranked and compared on the individual leaderboards provided by our open framework.
With the advent of global warming and energy crisis, the search for renewable energy to reduce carbon emissions has become one of the most urgent challenges. Ithas become a research hotspot to collect or harvest various mechanical energy in nature and convert it into electric energy. Vibration is a common form of mechanical movement in our daily life. It is visible both on most working machines and in nature and is a type of potential energy. There are several methods that can convert such mechanical energy into electric energy. Triboelectric nanogenerator (TENG) based on the principle of contact electrification and electrostatic induction which first appeared in 2012 by Zhonglin Wang provides a feasible method of efficiently collecting the vibrational energy with different vibrating frequencies. In this paper, a contact-separation mode of TENG is designed and implemented. The voltage- quantity of charge- distance(V-Q-x)relation of TENG is calculated. During the experiment, the factors such as load resistance, vibration frequency, etc. which affect the output performance, are considered and analyzed. An electrically driven crank-connecting rod mechanism is employed to provide the vibration source with adjustable frequency in a range of 1-6 Hz. The result shows that the amount of charge transfer in each working cycle remains almost unchanged, while the voltage and current increase with frequency increasing. When the frequency is 5 Hz, the best power matching resistance of the TENG is about 33 MΩ and the maximum output power reaches 0.5 mW. For a further study, a COMSOL software is used to simulate the distribution rule and variation rule of the electric potential in the contact-separation process, then the theoretical charge density and the experimental charge density on the polymer surface are compared and analyzed in order to provide theoretical and practical support for the design of TENG with collected vibration energy and self-powered vibration sensor. The result shows that the electric potential is proportional to the distance between two friction layers. While as the distance between two friction layers increases, the electric potential and the charge density both show a tendency to concentrate in the middle of the friction layer. The huge difference between experimental result and the simulation predicts thatmuch work should be done continually to improve the output of the TENG. Finally, the obtained results conduce to understanding the contact electrification and electrostatic induction mechanism and also provide a new method of harvesting the vibration energy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.