Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels.

Space mean speed cannot be directly measured in the field, although it is a basic parameter that is used to evaluate traffic conditions. An end-to-end convolutional neural network (CNN) was adopted to measure the space mean speed based solely on two consecutive road images. However, tagging images with labels (=true space mean speeds) by manually positioning and tracking every vehicle on road images is a formidable task. The present study was focused on naïve animation images provided by a traffic simulator, because these contain perfect information concerning vehicle movement to attain labels. The animation images, however, seem far-removed from actual photos taken in the field. A cycle-consistent adversarial network (CycleGAN) bridged the reality gap by mapping the animation images into seemingly realistic images that could not be distinguished from real photos. A CNN model trained on the synthesized images was tested on real photos that had been manually labeled. The test performance was comparable to those of state-of-the-art motion-capture technologies. The proposed method showed that deep-learning models to measure the space mean speed could be trained without the need for time-consuming manual annotation.

Systematic control of experimental inconsistency in combinatorial materials science.

We developed a method to systematically control experimental inconsistency, which is one of the most troublesome and difficult problems in high-throughput combinatorial experiments. The topic of experimental inconsistency is never addressed, even though all scientists in the field of combinatorial materials science face this very serious problem. Experimental inconsistency and material property were selected as dual objective functions that were simultaneously optimized. Specifically, in an attempt to search for promising phosphors with high reproducibility, photoluminescence (PL) intensity was maximized, and experimental inconsistency was minimized by employing a multiobjective evolutionary optimization-assisted combinatorial materials search (MOEO combinatorial material search) strategy. A tetravalent manganese-doped alkali earth germanium/titanium oxide system was used as a model system to be screened using MOEO combinatorial materials search. As a result of MOEO reiteration, we identified a halide-detached deep red phosphor with improved PL intensity and reliable reproducibility.

Deep-Learning Technique To Convert a Crude Piezoresistive Carbon Nanotube-Ecoflex Composite Sheet into a Smart, Portable, Disposable, and Extremely Flexible Keypad.

An extremely simple bulk sheet made of a piezoresistive carbon nanotube (CNT)-Ecoflex composite can act as a smart keypad that is portable, disposable, and flexible enough to be carried crushed inside the pocket of a pair of trousers. Both a rigid-button-imbedded, rollable (or foldable) pad and a patterned flexible pad have been introduced for use as portable keyboards. Herein, we suggest a bare, bulk, macroscale piezoresistive sheet as a replacement for these complex devices that are achievable only through high-cost fabrication processes such as patterning-based coating, printing, deposition, and mounting. A deep-learning technique based on deep neural networks (DNN) enables this extremely simple bulk sheet to play the role of a smart keypad without the use of complicated fabrication processes. To develop this keypad, instantaneous electrical resistance change was recorded at several locations on the edge of the sheet along with the exact information on the touch position and pressure for a huge number of random touches. The recorded data were used for training a DNN model that could eventually act as a brain for a simple sheet-type keypad. This simple sheet-type keypad worked perfectly and outperformed all of the existing portable keypads in terms of functionality, flexibility, disposability, and cost.

Classification of crystal structure using a convolutional neural network.

A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.

An extremely simple macroscale electronic skin realized by deep machine learning.

Complicated structures consisting of multi-layers with a multi-modal array of device components, i.e., so-called patterned multi-layers, and their corresponding circuit designs for signal readout and addressing are used to achieve a macroscale electronic skin (e-skin). In contrast to this common approach, we realized an extremely simple macroscale e-skin only by employing a single-layered piezoresistive MWCNT-PDMS composite film with neither nano-, micro-, nor macro-patterns. It is the deep machine learning that made it possible to let such a simple bulky material play the role of a smart sensory device. A deep neural network (DNN) enabled us to process electrical resistance change induced by applied pressure and thereby to instantaneously evaluate the pressure level and the exact position under pressure. The great potential of this revolutionary concept for the attainment of pressure-distribution sensing on a macroscale area could expand its use to not only e-skin applications but to other high-end applications such as touch panels, portable flexible keyboard, sign language interpreting globes, safety diagnosis of social infrastructures, and the diagnosis of motility and peristalsis disorders in the gastrointestinal tract.