矢入 郁子

The design ICT systems that can provide application services that quickly and flexibly integrate network and software is currently the key method in DX based on ICT. Non-etheless, the problem of the huge amount of time required for the automatic design of ICT systems has been paid more and more attention. Considering the rapidly changing demand for ICT systems in various industries, the need to build and monitor systems frequently, and the difficulty in securing engineers due to the declining birthrate and aging population, the huge design time problem cannot be ignored, especially if AI is expected to reduce design time. To this end, we study the problem of reducing the design time of ICT systems with deep reinforcement learning algorithms , Weaver. First of all, we set the graph neural network as the learning model, so that deep reinforcement learning algorithm is used to solve this problem. Secondly, we have designed an algorithm that combines the representative reinforcement learning algorithm Double DQN and Noisy Network. Then, we attempted to shorten the design time by changing the normal distribution to a truncated normal distribution at the optimal value among them. Finally, sufficient trials are conducted to verify our proposed method. The results show that, the proposed method reduces the learning time required to complete learning of the design.

In pursuing an intelligent society, the deployment of Beyond 5G/6G is anticipated. A crucial aspect of realizing this vision lies in establishing a robust non-terrestrial network encompassing satellite-based communication systems. However, space-based communication faces challenges from atmospheric disturbances. For instance, Ka-band, a crucial frequency range for satellite communication, is attenuated by rain. Similarly, optical satellite communication links are disrupted by clouds. To ensure reliable and high-quality communication, it is imperative to accurately predict the impact of weather on signal propagation, enabling the selection of ground stations and modulation methods. This research focuses on developing a predictive model for radio wave attenuation during space-to-ground communication, leveraging data from meteorological satellites. The model's core is a deep learning architecture that integrates CNNs, renowned for their proficiency in image feature extraction. The rain attenuation prediction with this model achieved a high coefficient of determination. In addition, to improve the prediction accuracy, we analyzed the complex relationship between the radio wave reception strength and Himawari standard data, a comprehensive dataset acquired from the Himawari meteorological satellite.

Objective sleep deprivation detection can enhance workplace safety and productivity in professions that require long working hours. To address this, we proposed deep learning models for classifying sleep-deprived individuals using EEG data. In this study, we utilized resting-state EEG data collected from both sleep-deprived and well-rested participants and generated five datasets (EyesClosed, EyesOpen-Raw, EyesOpen-AR, EyesClosed+EyesOpen-Raw, and EyesClosed+EyesOpen-AR), then applied them to 1D CNN and 1D CNN-LSTM models. Both models achieved their peak performance with EyesOpen-AR, which slightly outperformed EyesOpen-Raw, while demonstrating comparable performance across all datasets. Applying feature extraction using differential entropy within delta, theta, alpha, and beta bands to the five datasets resulted in decreased performance. The results suggest that artifact-removal from EyesOpen-Raw is not essential for sleep deprivation detection using deep learning models. Additionally, they suggest that 1D CNN may be a more suitable choice for sleep deprivation detection, and non-feature-extracted data is more suitable than feature-extracted data.

Electroencephalography (EEG)-based emotion recognition offers a noninvasive, cost-effective approach with applications in psychology, healthcare, and education. Accurate recognition of fear emotions is crucial for diagnosing and treating conditions such as phobias and anxiety disorders. This study classifies fear emotions into four levels using the DEAP dataset, leveraging Graph Neural Networks (GNNs) integrated with Long-Short-Term Memory (LSTM) networks. Two architectures, GIN-LSTM and ECLGCNN, were evaluated with raw EEG signals and Differential Entropy (DE) features. Performance was assessed using 10-fold and Leave-One-Subject-Out (LOSO) cross-validation, achieving a peak accuracy of 99.23% in 10-fold CV and 36.57% in LOSO CV, both surpassing prior studies. However, the LOSO results reveal limited generalizability to unseen subjects, highlighting the need for further research to enhance adaptability and robustness. This study demonstrates the potential of GNN-LSTM models for fear emotion classification and underscores the importance of addressing inter-subject variability to improve real-world applicability.

Graph neural networks, deep learning models designed for non-Euclidean data, have garnered attention in EEG-based emotion recognition. Recent studies explore EEG-based models and investigate multimodal models that incorporate peripheral physiological signals, such as electrooculography and electrocardiography, with ongoing research focused on feature fusion methods. The graphs used in GNNs for emotion recognition are generally constructed based on the spatial distance or the functional connectivity between channels; however, most models rely on only one type. This paper validates the effectiveness of a model that utilizes features from heterogeneous graphs and investigates various fusion methods inspired by multimodal approaches. As a result, the highest accuracy achieved was 93.87%, approximately 2% higher than that obtained using a single graph and comparable to existing methods. Furthermore, when synthesizing heterogeneous graphs, a technique that uses the embedding vector of the entire graph has proven to be more effective than one that considers individual channels.

Background Imagination represents a pivotal capability of human intelligence. To develop human-like artificial intelligence, uncovering the computational architecture pertinent to imaginative capabilities through reverse engineering the brain's computational functions is essential. The existing Structure-Constrained Interface Decomposition (SCID) method, leverages the anatomical structure of the brain to extract computational architecture. However, its efficacy is limited to narrow brain regions, making it unsuitable for realizing the function of imagination, which involves diverse brain areas such as the neocortex, basal ganglia, thalamus, and hippocampus. Objective In this study, we proposed the Function-Oriented SCID method, an advancement over the existing SCID method, comprising four steps designed for reverse engineering broader brain areas. This method was applied to the brain's imaginative capabilities to design a hypothetical computational architecture. The implementation began with defining the human imaginative ability that we aspire to simulate. Subsequently, six critical requirements necessary for actualizing the defined imagination were identified. Constraints were established considering the unique representational capacity and the singularity of the neocortex's modes, a distributed memory structure responsible for executing imaginative functions. In line with these constraints, we developed five distinct functions to fulfill the requirements. We allocated specific components for each function, followed by an architectural proposal aligning each component with a corresponding brain organ. Results In the proposed architecture, the distributed memory component, associated with the neocortex, realizes the representation and execution function; the imaginary zone maker component, associated with the claustrum, accomplishes the dynamic-zone partitioning function; the routing conductor component, linked with the complex of thalamus and basal ganglia, performs the manipulation function; the mode memory component, related to the specific agranular neocortical area executes the mode maintenance function; and the recorder component, affiliated with the hippocampal formation, handles the history management function. Thus, we have provided a fundamental cognitive architecture of the brain that comprehensively covers the brain's imaginative capacities.

In recent years, flow experience has been regarded as an important criterion for ideal user experience (UX), and is gaining attention in the design phase of video games. However, flow experience is mainly measured by subjective evaluations such as post-questionnaires, making it difficult to measure in real time. This study aims to investigate the relationship between the cognitive workload obtained by EEG measurement, the user's subjective flow experience score, EEG, and electrocardiogram. This paper conducted an experiment using the Tetris® Effect: Connected, and obtained the flow scores calculated from the ECG data, EEG data, and post-questionnaire, and analyzed them in detail. The results showed that the cognitive workload calculated from FC3 in the extended 10-20 method was likely to be related to the flow experience. It was also suggested that the parasympathetic index might be related to the flow experience under certain conditions.

The ability to continuously monitor cognitive workload associated with different tasks is crucial for understanding and evaluating user engagement. Electroencephalogram (EEG) is identified as one of the most promising indexes for measuring workload due to its high temporal resolution. However, EEG is usually buried under various noises and often requires preprocessing to obtain clean data for analysis. The purpose of this study is to propose a deep learning model suitable for estimating cognitive workload from raw EEG signals without using any preprocessing techniques. Specifically, the dataset consisted of EEG from two cognitive tasks, and the workload was calculated from Auditory Steady State Response (ASSR) which was used as input label. Comparing the performance of a 1D CNN and 1D CNN-LSTM model, both models achieved around 91.5% accuracy for the classification task, and the 1D CNN-LSTM model stood out achieving a R-squared of 0.991 for the regression task.

Objective and accurate classification of fear levels is a socially important task that contributes to developing treatments for Anxiety Disorder, Obsessive–compulsive Disorder, Post-Traumatic Stress Disorder (PTSD), and Phobia. This study examines a deep learning model to automatically estimate human fear levels with high accuracy using multichannel EEG signals and multimodal peripheral physiological signals in the DEAP dataset. The Multi-Input CNN-LSTM classification model combining Convolutional Neural Network (CNN) and Long Sort-Term Memory (LSTM) estimated four fear levels with an accuracy of 98.79% and an F1 score of 99.01% in a 10-fold cross-validation. This study contributes to the following; (1) to present the possibility of recognizing fear emotion with high accuracy using a deep learning model from physiological signals without arbitrary feature extraction or feature selection, (2) to investigate effective deep learning model structures for high-accuracy fear recognition and to propose Multi-Input CNN-LSTM, and (3) to examine the model’s tolerance to individual differences in physiological signals and the possibility of improving accuracy through additional learning.

This research had EEG measurement experiment using images and odor stimuli with the aim of establishing method for reading affection and aversion from brain information. In an odorless state, affection is distinguishable by existence of P600. It may be difficult to distinguish between indifference and aversion in an odorless state. N200 appeared more clearly when a bad odor was presented than in an odorless state or when presented with an aroma. This suggests the possibility of distinguishing preferences by looking at N200. It is thought to be possible to discriminate preferences by pattern matching by looking at N400 and P600. When presenting an aroma, only affection can be distinguished by looking at P600. This result is expected to be applied to marketing. In this research, N400 which had not been focused on in previous studies was observed. The possibility that N400 was some kind of reaction related to preference was found.

Path integration is one of the functions that support the self-localization ability of animals. Path integration outputs position information after an animal’s movement when initial-position and movement information is input. The core region responsible for this function has been identified as the medial entorhinal cortex (MEC), which is part of the hippocampal formation that constitutes the limbic system. However, a more specific core region has not yet been identified. This research aims to clarify the detailed structure at the cell-firing level in the core region responsible for path integration from fragmentarily accumulated experimental and theoretical findings by reviewing 77 papers. This research draws a novel diagram that describes the MEC, the hippocampus, and their surrounding regions by focusing on the MEC’s input/output (I/O) information. The diagram was created by summarizing the results of exhaustively scrutinizing the papers that are relative to the I/O relationship, the connection relationship, and cell position and firing pattern. From additional investigations, we show function information related to path integration, such as I/O information and the relationship between multiple functions. Furthermore, we constructed an algorithmic hypothesis on I/O information and path-integration calculation method from the diagram and the information of functions related to path integration. The algorithmic hypothesis is composed of regions related to path integration, the I/O relations between them, the calculation performed there, and the information representations (cell-firing pattern) in them. Results of examining the hypothesis confirmed that the core region responsible for path integration was either stellate cells in layer II or pyramidal cells in layer III of the MEC.

Providing accessibility information about sidewalks for people with difficulties with moving is an important social issue. We previously proposed a fully supervised machine learning approach for providing accessibility information by estimating road surface conditions using wheelchair accelerometer data with manually annotated road surface condition labels. However, manually annotating road surface condition labels is expensive and impractical for extensive data. This paper proposes and evaluates a novel method for estimating road surface conditions without human annotation by applying weakly supervised learning. The proposed method only relies on positional information while driving for weak supervision to learn road surface conditions. Our results demonstrate that the proposed method learns detailed and subtle features of road surface conditions, such as the difference in ascending and descending of a slope, the angle of slopes, the exact locations of curbs, and the slight differences of similar pavements. The results demonstrate that the proposed method learns feature representations that are discriminative for a road surface classification task. When the amount of labeled data is 10% or less in a semi-supervised setting, the proposed method outperforms a fully supervised method that uses manually annotated labels to learn feature representations of road surface conditions.

Recent expansion of intelligent gadgets, such as smartphones and smart watches, familiarizes humans with sensing their activities. We have been developing a road accessibility evaluation system inspired by human sensing technologies. This paper introduces our methodology to estimate road accessibility from the three-axis acceleration data obtained by a smart phone attached on a wheelchair seat, such as environmental factors, e.g., curbs and gaps, which directly influence wheelchair bodies, and human factors, e.g., wheelchair users’ feelings of tiredness and strain. Our goal is to realize a system that provides the road accessibility visualization services to users by online/offline pattern matching using impersonal models, while gradually learning to improve service accuracy using new data provided by users. As the first step, this paper evaluates features acquired by the DCNN (deep convolutional neural network), which learns the state of the road surface from the data in supervised machine learning techniques. The evaluated results show that the features can capture the difference of the road surface condition in more detail than the label attached by us and are effective as the means for quantitatively expressing the road surface condition. This paper developed and evaluated a prototype system that estimated types of ground surfaces focusing on knowledge extraction and visualization.