arXiv subjects

Hiroshi Tokieda

Publications and source records attributed to Hiroshi Tokieda.

3 recordsLinked to original sources

arXiv2023

Performance of prototype Dual Gain Multilayer Thick GEM with high-intensity heavy-ion beam injections in low-pressure hydrogen gas

A prototype Dual Gain Multilayer Thick Gas Electron Multilyer (DG-M-THGEM) with an active area of 10 cm $\times$ 10 cm was manufactured aiming at the production of a large-volume active-target time projection chamber which can work under the condition of high-intensity heavy-ion beam injections. The DG-M-THGEM has a alternating structure of electrodes and insulators. Effective gas gains of two regions, which are called beam and recoil regions, are separately controlled. Performance of the prototype DG-M-THGEM in hydrogen gas at a pressure of 40 kPa was evaluated. Irradiating a $^{132}$Xe beam, an effective gas gain lower than 100 with a charge resolution of 3% was achieved in the beam region while the effective gas gain of 2000 was maintained in the recoil region. Position distributions of measured charges along the beam axis were investigated in order to evaluate gain uniformity in the high intensity beam injection. The gain shift was estimated by simulations considering space charges in the drift region. The gain shift was suppressed within 3% even at the beam intensity of 2.5 $\times$ 10$^{6}$ particles per second.

physics.ins-det↗

arXiv2020

Model Bridging: Connection between Simulation Model and Neural Network

The interpretability of machine learning, particularly for deep neural networks, is crucial for decision making in real-world applications. One approach is replacing the un-interpretable machine learning model with a surrogate model, which has a simple structure for interpretation. Another approach is understanding the target system by using a simulation modeled by human knowledge with interpretable simulation parameters. Recently, simulator calibration has been developed based on kernel mean embedding to estimate the simulation parameters as posterior distributions. Our idea is to use a simulation model as an interpretable surrogate model. However, the computational cost of simulator calibration is high owing to the complexity of the simulation model. Thus, we propose a ''model-bridging'' framework to bridge machine learning models with simulation models by a series of kernel mean embeddings to address these difficulties. The proposed framework enables us to obtain predictions and interpretable simulation parameters simultaneously without the computationally expensive calculations of the simulations. In this study, we apply the proposed framework to essential simulations in the manufacturing industry, such as production simulation and fluid dynamics simulation.

stat.ML↗

arXiv2020

A copula-based visualization technique for a neural network

Interpretability of machine learning is defined as the extent to which humans can comprehend the reason of a decision. However, a neural network is not considered interpretable due to the ambiguity in its decision-making process. Therefore, in this study, we propose a new algorithm that reveals which feature values the trained neural network considers important and which paths are mainly traced in the process of decision-making. In the proposed algorithm, the score estimated by the correlation coefficients between the neural network layers that can be calculated by applying the concept of a pair copula was defined. We compared the estimated score with the feature importance values of Random Forest, which is sometimes regarded as a highly interpretable algorithm, in the experiment and confirmed that the results were consistent with each other. This algorithm suggests an approach for compressing a neural network and its parameter tuning because the algorithm identifies the paths that contribute to the classification or prediction results.

cs.LG↗