KUKeiichi Ueda

Keiichi Ueda

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Keiichi Ueda has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Estimation of 28 GHz Band Wave Propagation using Machine Learning

    by Yuta Watanabe, Keiichi Ueda

    This paper presents estimation of 28 GHz band wave propagation using machine learning. Electromagnetic waves in millimeter wave (mmWave) band, such as 28 and 39 GHz, are used for 5G communications. Because electromagnetic waves in the mmWave band are affected by obstructions, estimation of radio propagation is necessary. In this study, we use machine learning to estimate the wave propagation of electromagnetic waves in the 28 GHz band in order to estimate the effect of obstacles. The analytical model and results obtained by the ray tracing method was used as the training data for the machine learning. The results obtained by the convolutional neural network yielded good estimates. Its coefficient of determination was 0.91.

  • Open Access

    AI‐Equipped Scanning Probe Microscopy for Autonomous Site‐Specific Atomic‐Level Characterization at Room Temperature

    by Zhuo Diao, Keiichi Ueda, Linfeng Hou, Fengxuan Li, Hayato Yamashita, Masayuki Abe

    An advanced scanning probe microscopy system enhanced with artificial intelligence (AI‐SPM) designed for self‐driving atomic‐scale measurements is presented. This system expertly identifies and manipulates atomic positions with high precision, autonomously performing tasks such as spectroscopic data acquisition and atomic adjustment. An outstanding feature of AI‐SPM is its ability to detect and adapt to surface defects, targeting or avoiding them as necessary. It is also designed to overcome typical challenges such as positional drift and tip apex atomic variations due to the thermal effects, ensuring accurate, site‐specific surface analysis. The tests under the demanding conditions of room temperature have demonstrated the robustness of the system, successfully navigating thermal drift and tip fluctuations. During these tests on the Si(111)‐(7 × 7) surface, AI‐SPM autonomously identified defect‐free regions and performed a large number of current–voltage spectroscopy measurements at different adatom sites, while autonomously compensating for thermal drift and monitoring probe health. These experiments produce extensive data sets that are critical for reliable materials characterization and demonstrate the potential of AI‐SPM to significantly improve data acquisition. The integration of AI into SPM technologies represents a step toward more effective, precise and reliable atomic‐level surface analysis, revolutionizing materials characterization methods.


  • Existence probabilities of single Si atoms diffusing in Si(111)-(7 × 7) half-unit cells at room temperature

    by K. Ueda, Z. Diao, L. Hou, H. Yamashita, M. Abe

    We determined the probabilities of finding diffusing Si atoms in faulted and unfaulted half-unit cells on the Si(111)-(7 × 7) surface. An adsorbed Si atom on the surface at room temperature moved in the half-unit cells. The atom was adsorbed via atom manipulation and located via under-sampled scanning tunneling microscopy. Images of the half-unit cells with the diffusing Si atom and images of the clean surface were superimposed via image processing to calculate differences used to determine the Si atom positions at room temperature. There were different probabilities for Si atom diffusion in faulted and unfaulted half-unit cells.


  • Feature correlation method for image reconstruction evaluation in under-sampled scanning probe microscopy

    by Keiichi Ueda, Zhuo Diao, Linfeng Hou, Hayato Yamashita, Masayuki Abe

    We introduce an advanced feature-correlation approach for evaluating the accuracy of data completion in scanning probe microscopy (SPM). Our method utilizes characteristic patterns from conventional SPM images and their reconstructions via data interpolation. We develop a refined comparative evaluation algorithm based on correlation coefficients. This algorithm provides a precise assessment by effectively addressing SPM-specific distortions such as thermal drift, feedback error, and noise limitations often overlooked by traditional metrics such as peak signal-to-noise ratio and structural similarity index measure. The effectiveness of our approach is demonstrated through its application in high-resolution and extensive scanning tunneling microscopy assessments.

  • Automatic drift compensation for nanoscale imaging using feature point matching

    by Zhuo Diao, Keiichi Ueda, Linfeng Hou, Hayato Yamashita, Oscar Custance, Masayuki Abe

    An implementation of drift compensation for imaging at the nanoscale is presented. The method is based on computer vision techniques and hence applicable to any microscope that generates images through a computer interface. The algorithm extracts and matches pairs of feature points from consecutive images to compute and compensate for probe–sample misalignments over time. The protocol also applies selection rules that enable it to withstand significant changes in image contrast. We demonstrate our fully automatic implementation by continuously imaging the same area of a Si(100) surface at the atomic scale with scanning probe microscopy over a period of 25 h at room temperature, showing that the method is robust even under the presence of non-linear drift or spontaneous changes of the probe apex. We apply our method to study the movement of pairs of tin atoms confined within a half-unit cell of the Si(111)-(7 × 7) surface and estimate the energy barrier for their diffusion at room temperature.


  • 10.1063/5.0139330.1

    by Zhuo Diao, Keiichi Ueda, Linfeng Hou, Hayato Yamashita, Oscar Custance

    An implementation of drift compensation for imaging at the nanoscale is presented. The method is based on computer vision techniques and hence applicable to any microscope that generates images through a computer interface. The algorithm extracts and matches pairs of feature points from consecutive images to compute and compensate for probe–sample misalignments over time. The protocol also applies selection rules that enable it to withstand significant changes in image contrast. We demonstrate our fully automatic implementation by continuously imaging the same area of a Si(100) surface at the atomic scale with scanning probe microscopy over a period of 25 h at room temperature, showing that the method is robust even under the presence of non-linear drift or spontaneous changes of the probe apex. We apply our method to study the movement of pairs of tin atoms confined within a half-unit cell of the Si(111)-(7 × 7) surface and estimate the energy barrier for their diffusion at room temperature.

  • Open Access

    Room-temperature-concerted switch made of a binary atom cluster

    by Eiichi Inami, Ikutaro Hamada, Keiichi Ueda, Masayuki Abe, Seizo Morita, Yoshiaki Sugimoto

    Single-atom/molecule manipulation for fabricating an atomic-scale switching device is a promising technology for nanoelectronics. So far, scanning probe microscopy studies have demonstrated several atomic-scale switches, mostly in cryogenic environments. Although a high-performance switch at room temperature is essential for practical applications, this remains a challenging obstacle to overcome. Here we report a room-temperature switch composed of a binary atom cluster on the semiconductor surface. Distinctly different types of manipulation techniques enable the construction of an atomically defined binary cluster and the electronic switching of the conformations, either unidirectionally or bidirectionally. The switching process involves a complex rearrangement of multiple atoms in concerted manner. Such a feature is strikingly different from any switches mediated by single-atom/molecule processes that have been previously reported.


  • Three-dimensional scanning force/tunneling spectroscopy at room temperature

    by Yoshiaki Sugimoto, Keiichi Ueda, Masayuki Abe, Seizo Morita

    We simultaneously measured the force and tunneling current in three-dimensional (3D) space on the Si(111)-(7 × 7) surface using scanning force/tunneling microscopy at room temperature. The observables, the frequency shift and the time-averaged tunneling current were converted to the physical quantities of interest, i.e. the interaction force and the instantaneous tunneling current. Using the same tip, the local density of states (LDOS) was mapped on the same surface area at constant height by measuring the time-averaged tunneling current as a function of the bias voltage at every lateral position. LDOS images at negative sample voltages indicate that the tip apex is covered with Si atoms, which is consistent with the Si-Si covalent bonding mechanism for AFM imaging. A measurement technique for 3D force/current mapping and LDOS imaging on the equivalent surface area using the same tip was thus demonstrated.