Kazushi Ikeda

• PhD in Engineering
• Professor at Nara Institute of Science and Technology

Lifeline utility networks have been studied extensively within the domain of network reliability due to the prevalence of natural hazards. The reliability of these networks is typically investigated through graphs that retain their structural characteristics. This paper introduces novel connectivity-based reliability measures tailored for stochasti...

Graph neural networks (GNNs) have gained significant attention in recent years for their ability to process data that may be represented as graphs. This has prompted several studies to explore their representational capability based on the graph isomorphism task. Notably, these works inherently assume a countable node feature representation, potent...

Wearable thermoelectric devices offer a transformative approach to energy harvesting, providing sustainable solutions for powering next-generation technologies. In pursuit of efficient, flexible, biocompatible, and cost-effective thermoelectric materials, zinc oxide (ZnO) has emerged as a distinctive candidate due to its unique combination of favor...

Recent progress in data analysis and machine learning has enabled the efficient processing of large data; however, the public sector has yet to fully adopt these advancements. The study investigates the application of dynamic principal component analysis in offering real-time insights into various facets of an economy, potentially aiding in the inf...

The zero-suppressed binary decision diagram (ZDD) is a compact data structure widely used for the efficient representation of families of sparse subsets. Its inherent recursive structure also facilitates easy diagram manipulation and family operations. Practical applications generally fall under discrete optimization, such as combinatorial problems...

Wearable thermoelectric generators (WTEG), being flexible and safe, are the only replacement for conventional batteries for IoT-based wearable electronic devices. In WTEGs, the human body heat and atmospheric temperature are used to maintain a thermal gradient across the device which in turn produces electrical energy. In order to achieve an effici...

Graph neural networks (GNNs) have gained significant attention in recent years for their ability to process data that may be represented as graphs. This has prompted several studies to explore their representational capability based on the graph isomorphism task. Notably, these works inherently assume a countable node feature representation, potent...

Machine learning techniques are based on stochastic models associated with parameter estimation from massive data. They have been applied to scientific fields as well as industries, including mobility analyses. In this chapter, we introduce several machine learning techniques for mobility analyses, that is, techniques to track agents in a video, to...

The pancake graph has served as a model for real-world networks due to its unique recursive and symmetric properties. Defined as the Cayley graph on the symmetric group of order n generated by prefix reversals, the n-pancake graph exhibits a rapid increase in the number of vertices and edges with respect to order n. While there are considerable gra...

Estimating the pose of multiple objects has improved substantially since deep learning became widely used. However, the performance deteriorates when the objects are highly similar in appearance or when occlusions are present. This issue is usually addressed by leveraging temporal information that takes previous frames as priors to improve the robu...

Understanding the principles of cell migration necessitates measurements of the forces generated by cells. In traction force microscopy (TFM), fluorescent beads are placed on a substrate’s surface and the substrate strain caused by the cell traction force is observed as displacement of the beads. Mathematical analysis can estimate traction force fr...

Lifeline utility networks have been studied extensively within the domain of network reliability due to the prevalence of natural hazards. The reliability of these networks is typically investigated through graphs that retain their structural characteristics. This paper introduces novel connectivity-based reliability measures tailored for stochasti...

Background Phenotyping analysis that includes time course is useful for understanding the mechanisms and clinical management of postoperative delirium. However, postoperative delirium has not been fully phenotyped. Hypothesis-free categorization of heterogeneous symptoms may be useful for understanding the mechanisms underlying delirium, although e...

In working toward the goal of uncovering the inner workings of the brain, various imaging techniques have been the subject of research. Among the prominent technologies are devices that are based on the ability of transgenic animals to signal neuronal activity through fluorescent indicators. This paper investigates the utility of an original ultra-...

Gaze behavior of human coders could allow to improve programmer-aiding tools relying on program comprehension algorithms, as gaze reveals which subsets of source code programmers focus on to understand its function. When real gaze data are unavailable, algorithmic solutions for gaze behavior estimation might be used to integrate gaze behavior in a...

Recent advanced driver assistance systems’ (ADASs) control cars to avoid accidents, but few of them consider driver’s comfort. To realize comfortable driving, an ADAS must sense the driver’s emotions, especially when they are negative. Since emotions are reflected in a person’s physiological signals, they are informative for sensing emotions. Howev...

The Japan Electric Power Exchange (JEPX) provides a platform for the trading of electric energy in a manner similar to more traditional financial markets. As the number of market agents increase, there is an increasing need for effective price-forecasting models. Electricity price data are observed to exhibit periods of relatively stable, i.e., low...

Limitations in simultaneously observing the activity of multiple molecules in live cells prevent researchers from elucidating how these molecules coordinate the dynamic regulation of cellular functions. Here, we propose the motion-triggered average (MTA) algorithm to characterize pseudo-simultaneous dynamic changes in arbitrary cellular deformation...

In the digital era, new socially shared realities and norms emerge rapidly, whether they are beneficial or harmful to our societies. Although these are emerging properties from dynamic interaction, most research has centered on static situations where isolated individuals face extant norms. We investigated how perceptual norms emerge endogenously a...

Multi-instance object tracking is an active research problem in computer vision, where most novel methods analyze and locate targets on videos taken from static camera set-ups, just as many existing monitoring systems worldwide. These have proved efficient and effective for many established monitoring systems worldwide, such as animal behavior stud...

Establishing toxicological predictive modeling frameworks for heterogeneous nanomaterials is crucial for rapid environmental and health risk assessment. However, existing structure-toxicity correlation models for such nano- materials are only based on simple linear regression algorithms that are prone to underfitting the training data. These models...

To facilitate the reuse of environmental waste heat in our society, we have developed high-efficiency flexible thermoelectric power generators (TEPGs). In this study, we investigated the thermoelectromotive force (TEMF) and output power of a prototype device with 50 pairs of Π-type structures using a homemade measurement system for flexible TEPGs i...

Fecal incontinence is a serious but popular problem for elderly people since it not only degrades their quality of physical and mental life but also increases the work of care givers. One promising tool to solve this problem is a defecation prediction system since a patient can go to toilet if he/she knows the time of excretion in advance. Our appr...

This work presents machine learning (ML) assisted Fermi level prediction of solution‐processed ultra‐wide bandgap (UWB) amorphous gallium oxide (a‐Ga2Ox) which can significantly accelerate the fabrication of semiconducting UWB a‐Ga2Ox‐based material for future display application. Different models such as Kernel Ridge Regression (KRR), Support Vect...

ZnO nanostructures were grown on carbon fabric with and without a capping agent using a simple hydrothermal method, and the growth times were varied in order to study the effect of the capping agent. The formation of ZnO wurtzite nanostructures was observed from the structural analysis of the sample with a capping agent. Morphological and mapping a...

Physiological measurements of dogs' emotional states during human-animal interactions are essential for understanding the underlying biological relationship. Heart rate measured by electrocardiogram (ECG) can be used for the physiological measurement of emotional state. Soft disposable electrodes, which can be purchased commercially and reduce the...

Various measures that characterize graphs exist in literature. Insights into the properties of a graph as a whole and its components are revealed largely through graph measures, also called graph metrics. In seeking to interpret a consequential edge metric from a vertex-centric perspective, the paper advances an original measure - the relative isol...

The pancake graph has been the subject of research. While studies on the various aspects of the graph are abundant, results on the chromatic properties may be further enhanced. Revolving around such context, the paper advances an alternative method to produce novel linear bounds for the vertex chromatic number of the pancake graph. The accompanying...

Graphs are a highly expressive data structure, but it is often difficult for humans to find patterns from a complex graph. Hence, generating human-interpretable sequences from graphs have gained interest, called graph2seq learning. It is expected that the compositionality in a graph can be associated to the compositionality in the output sequence i...

Our current understanding of melancholic depression is shaped by its position in the depression spectrum. The lack of consensus on how it should be treated—whether as a subtype of depression, or as a distinct disorder altogethe—interferes with the recovery of suffering patients. In this study, we analyzed brain state energy landscape models of mela...

Graph neural networks (GNNs) have been widely used to learn vector representation of graph-structured data and achieved better task performance than conventional methods. The foundation of GNNs is the message passing procedure, which propagates the information in a node to its neighbors. Since this procedure proceeds one step per layer, the range o...

Managing depression relapse is a challenge given factors such as inconsistent follow-up and cumbersome psychological distress evaluation methods which leaves patients with a high risk of relapse to leave their symptoms untreated. In an attempt to bridge this gap, we proposed an approach on the use of personal longitudinal lifelog activity data gath...

The inability to simultaneously observe all of the important Rho GTPases (Cdc42, Rac1, and RhoA) has prevented us from obtaining evidence of their coordinated regulation during cell deformation. Here, we propose Motion-Triggered Average (MTA), an algorithm that converts individually observed GTPases into pseudo-simultaneous observations. Using the...

Graph neural networks (GNNs) have been widely used to learn vector representation of graph-structured data and achieved better task performance than conventional methods. The foundation of GNNs is the message passing procedure, which propagates the information in a node to its neighbors. Since this procedure proceeds one step per layer, the scope o...

The article Herding mechanisms to maintain the cohesion of a harem group.

A wide range of problems in operations research falls under arc routing problems, a domain which focuses on arc or edge features rather than node or vertex attributes. The undirected rural postman problem is a well-known problem in arc routing that seeks to determine a minimum cost walk that traverses a certain set of required edges on a given grap...

Expertise enables humans to achieve outstanding performance on domain-specific tasks, and programming is no exception. Many studies have shown that expert programmers exhibit remarkable differences from novices in behavioral performance, knowledge structure, and selective attention. However, the underlying differences in the brain of programmers ar...

Reinforcement learning has proved to be of great utility; execution , however, may be costly due to sampling inefficiency. An efficient method for training is experience replay, which recalls past experiences. Several experience replay techniques, namely, combined experience replay , hindsight experience replay, and prioritized experience replay, h...

Social norms, including values, beliefs and even perceptions about the world, are preserved and created through repeated interactions between individuals. However, whereas neuro-cognitive research on social norms has used the “unilateral influence” paradigm focusing on people’s reactions to extant standards, little is known about how our basic perc...

Extraction of complex temporal patterns, such as human behaviors, from time series data is a challenging yet important problem. The double articulation analyzer has been previously proposed by Taniguchi et al. to discover a hierarchical structure that leads to complex temporal patterns. It segments time series into hierarchical state subsequences,...

The paper sets forth a novel eigenvalue interlacing property across the finite-state birth-death process intensity matrix and two clearly identified submatrices as an extension of Cauchy's interlace theorem for Hermitian matrix eigenvalues. A supplemental proof involving an examination of probabilities acquired from specific movements across states...

Experiments with animal models of epilepsy have consistently shown that focal cooling of epilepsy-induced brain region reversibly suppresses or terminates epileptic discharge activity. Recently, we formulated a physiologically plausible temperature dependence in a neural mass model that can reproduce the effect of focal cooling on epileptic dischar...

In animal groups, individual interactions achieve coordinated movements to maintain cohesion. In horse-harem groups, herding is a behaviour in which stallions chase mares from behind; it is considered to assist with group cohesiveness. The mechanisms of the group cohesion were studied using the methods of drone filming and video tracking during her...

Heart rate variability (HRV) is a physical and noninvasive index of the autonomic nervous system and has been used in a wide range of fields such as human medicine, veterinary and animal behavior. Measuring devices have been improved miniaturization and light-weighting and they make it possible to measure a dog's electrocardiogram (ECG) under a fre...

Decision-diagram-based solutions for discrete optimization have been persistently studied. Among these is the use of the zero-suppressed binary decision diagram, a compact graph-based representation for a specified family of sets. Such a diagram may work out combinatorial problems by efficient enumeration. In brief, an extension to the frontier-bas...

Deep neural networks (DNNs) have the same structure as the neocognitron proposed in 1979 but have much better performance, which is because DNNs include many heuristic techniques such as pre-training, dropout, skip connections, batch normalization (BN), and stochastic depth. However, the reason why these techniques improve the performance is not fu...

Developing mathematical models for zinc oxide (ZnO) nanostructures can significantly accelerate the production of ZnO-based devices and applications. Herein, the implementation of supervised machine learning to predict the optical band gap energy of ZnO is presented. Different models such as Kernel Ridge Regression (KRR) and Artificial Neural Netwo...

Physiotherapy is a labor-intensive process that has become increasingly inaccessible. Existing telehealth solutions overcome many of the logistical problems, but they are cumbersome to re-calibrate for the various exercises involved. To facilitate self-exercise efficiently, we developed a framework for personalized physiotherapy exercises. Our appr...

Expertise enables humans to achieve outstanding performance on domain-specific tasks, and programming is no exception. Many have shown that expert programmers exhibit remarkable differences from novices in behavioral performance, knowledge structure, and selective attention.However, the underlying differences in the brain are still unclear. We here...

The ResNet skipping two layers (ResNet2) is known to have a smaller expected risk than that skipping one layer (ResNet1) or no layer (MLP), however, the mechanism of the small expected risk is still unclear. The expected risk is divided into the three components, the generalization gap, the optimization error, and the sample expressivity, and the l...

Deep neural networks such as multi-layer perceptron (MLP) have intensively been studied and new techniques have been introduced for better generalization ability and faster convergence. One of the techniques is skip-connections between layers in the ResNet and another is the batch normalization (BN). To clarify effects of these techniques, we carri...

Behavioral synchronization is shown not only between intra-species but also between inter-species. Previous studies reported that behavioral synchronization occurs between dogs and their owners by affiliative bonds and dogs' social skills for communicating with humans acquired by domestication. Horses also have such bonds and skills like dogs, howe...

In animal groups, individual interactions achieve coordinated movements to maintain cohesion. In horse harem groups, herding is a behavior in which males chase females from behind; it is considered to assist with group cohesiveness. However, the mechanisms by which the individuals move to maintain group cohesion are unknown. We applied novel non-in...

The relationship among three correlated variables could be very sophisticated, as a result, we may not be able to find their hidden causality and model their relationship explicitly. However, we still can make our best guess for possible mappings among these variables, based on the observed relationship. One of the complicated relationships among t...

Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well. To achieve better performance under less stringent requirements, we introduce a procedure which constructs a robust approximation of the risk gradient for us...

Emotional contagion is a primitive form of empathy that does not need higher psychological functions. Recent studies reported that emotional contagion exists not only between humans but also among various animal species. The dog (Canis familiaris) is a unique animal and the oldest domesticated species. Dogs have coexisted with humans for more than...

Program comprehension is a dominant process in software development and maintenance. Experts are considered to comprehend the source code efficiently by directing their gaze, or attention, to important components in it. However, reflecting importance of components is still a remaining issue in gaze behavior analysis for source code comprehension. H...

Understanding the contributions of therapist skill during intervention is essential for improving existing rehabilitation methodologies. This study aims to characterize therapist intervention on an important activity of daily living, the sit-to-stand motion. Using the concept of muscle synergy, we quantify and compare naturally-occurring standing s...

Estimation of the gradient of the logarithm of a probability density function is a versatile tool in statistical data analysis. A recent method for model-seeking clustering called the least-squares log-density gradient clustering (LSLDGC) [Sasaki et al., 2014] employs a sophisticated gradient estimator, which directly estimates the log-density grad...

Motor-skill learning for complex robotic tasks is a challenging problem due to the high task variability. Robotic clothing assistance is one such challenging problem that can greatly improve the quality-of-life for the elderly and disabled. In this study, we propose a data-efficient representation to encode task-specific motor-skills of the robot u...

This chapter introduces cyber-enhanced rescue canines that digitally strengthen the capability of search and rescue (SAR) dogs using robotics technology. A SAR dog wears a cyber-enhanced rescue canine (CRC) suit equipped with sensors (Camera, IMUs, and GNSS). The activities of the SAR dog and its surrounding view and sound are measured by the senso...

Studies on human interaction detection generally assume that interaction information is time-invariant. However, interaction may change over time, especially when time series dynamics is considered. To detect these switching interactions, we propose a segmentation-based approach. A method combining the segmentation of BP-AR-HMM and the double artic...

Most studies on human interaction detection have not considered causality. However , causal interaction detection in general is also of great interest, more so if the interaction involved changes over time. To detect these switching causal interactions , we propose a segmentation-based approach. A method combining the segmentation of BP-AR-HMM and...

Experience replay is used in deep reinforcement learning for sample-efficient learning by recalling past experiences. While relative merits are unclear , several experience replay algorithms have been crafted. In this study, one proposes hybrid replay algorithms and compares variations of experience replay incorporated into the Deep Q-Network algor...

This paper presents an augmenting path based online max-flow algorithm. The proposed algorithm handles graph changes in chunk manner, updating residual graph in response to edge capacity increase, decrease, edge/node adding and removal. All possible graph changes are abstracted into two key graph changes, which are capacity decrease and in- crease....

We propose a segmentation method for multiple related time series data using non-parametric Bayesian methods. This method assumes that human motion follows a double articulation structure, where low-level dynamical behaviors are discovered using beta process-autoregressive hidden Markov model (BP-AR-HMM), and high-level semantic behaviors are forme...

Biological cells express intracellular biomolecular information to the extracellular environment as various physical responses. We show a novel computational approach to estimate intracellular biomolecular pathways from growth cone electrophysiological responses. Previously, it was shown that cGMP signaling regulates membrane potential (MP) shifts...

Parallel incremental learning is an effective approach for rapidly processing large scale data streams, where parallel and incremental learning are often treated as two separate problems and solved one after another. Incremental learning can be implemented by merging knowledge from incoming data and parallel learning can be performed by merging kno...

Learning curves of simple perceptron were derived here. The learning curve of the perceptron learning with noisy teacher was shown to be non-monotonic, which has never appeared even though the learning curves have been analyzed for half a century. In this paper, we showed how this phenomenon occurs by analyzing the asymptotic property of the percep...

The covariance matrix of signals is one of the most essential information in multivariate analysis and other signal processing techniques. The estimation accuracy of a covariance matrix is degraded when some eigenvalues of the matrix are almost duplicated. Although the degradation is theoretically analyzed in the asymptotic case of infinite variabl...

Search and rescue dogs are widely used in disaster situations. The efficiency of their operations can be improved if the dogs' inner states or motivation to search are estimated. We developed a real-time emotion estimation system for canines based on a measured electrocardiogram. Interval time of heart beats were measured by our canine suit equippe...

A traditional classifier requires having training samples from each class. However, in reality, it is possible that the testing set may include classes that are not in the training set. This inevitably causes an issue: data from a undefined class will be assigned to a predefined classes. To tackle this, we propose a semi-supervised variational Gaus...

The relationship among three correlated variables could be very sophisticated, as a result, we may not be able to find their hidden causality and model their relationship explicitly. However, we still can make our best guess for possible mappings among these variables, based on the observed relationship. One of the complicated relationships among t...

Experiments with drug-induced epilepsy in rat brains and epileptic human brain region reveal that focal cooling can suppress epileptic discharges without affecting the brain’s normal neurological function. Findings suggest a viable treatment for intractable epilepsy cases via an implantable cooling device. However, precise mechanisms by which cooli...

For the regression task in a non-parametric setting, designing the objective function to be minimized by the learner is a critical task. In this paper we propose a principled method for constructing and minimizing robust losses, which are resilient to errant observations even under small samples. Existing proposals typically utilize very strong est...