Causal structure learning, also known as causal discovery, aims to estimate causal relationships between variables as a form of a causal directed acyclic graph (DAG) from observational data. One of the major frameworks is the order-based approach that first estimates a topological order of the underlying DAG and then prunes spurious edges from the fully-connected DAG induced by the estimated topological order. Previous studies often focus on the former ordering step because it can dramatically reduce the search space of DAGs. In practice, the latter pruning step is equally crucial for ensuring both computational efficiency and estimation accuracy. Most existing methods employ a pruning technique based on generalized additive models and hypothesis testing, commonly known as CAM-pruning. However, this approach can be a computational bottleneck as it requires repeatedly fitting additive models for all variables. Furthermore, it may harm estimation quality due to multiple testing. To address these issues, we introduce a new pruning method based on sparse additive models, which enables direct pruning of redundant edges without relying on hypothesis testing. We propose an efficient algorithm for learning sparse additive models by combining the randomized tree embedding technique with group-wise sparse regression. Experimental results on both synthetic and real datasets demonstrated that our method is significantly faster than existing pruning methods while maintaining comparable or superior accuracy.

Causal discovery from observational data is a fundamental tool in various fields of science. While existing approaches are typically designed for a single dataset, we often need to handle multiple datasets with non-identical variable sets in practice. One straightforward approach is to estimate a causal graph from each dataset and construct a single causal graph by overlapping. However, this approach identifies limited causal relationships because unobserved variables in each dataset can be confounders, and some variable pairs may be unobserved in any dataset. To address this issue, we leverage Causal Additive Models with Unobserved Variables (CAM-UV) that provide causal graphs having information related to unobserved variables. We show that the ground truth causal graph has structural consistency with the information of CAM-UV on each dataset. As a result, we propose an approach named I-CAM-UV to integrate CAM-UV results by enumerating all consistent causal graphs. We also provide an efficient combinatorial search algorithm and demonstrate the usefulness of I-CAM-UV against existing methods.

Bayesian networks can deduce statistical causal relationships from observed data. When applied to a large-scale health and medical dataset, it becomes feasible to employ the deduced networks to identify potential factors related to disease onset. Factors contributing to the onset of lifestyle-related diseases, such as the social environment and habits, vary significantly among individuals. Thus, it can be hypothesized that networks illustrating disease onset mechanisms would also exhibit substantial diversity. However, typical statistical causal discovery methods challenge the analysis of relationships specific to the sub-groups in a dataset because they use the entire data. In response to this, we use a pattern mining technique for Iwaki Health Promotion Project Health Checkup data to derive subgroups exhibiting strong correlations with the target variables. We estimated the Bayesian networks for the characteristic subgroups out of those derived, and compared them with the Bayesian network estimated for the total (hereafter, base network). Our target was the onset of eight lifestyle-related diseases within three years, resulting in a total of 359 subgroups. By comparing the estimated subgroup networks with the base network, we confirmed the numerous relationships specific to the subgroup networks. These encompassed not only clinically known but also non-trivial relationships. Our approach, which uses target-wise correlation-based rule subgrouping and network estimation is beneficial for constructing hypotheses on the differences in disease onset causes among potential subgroups.

Machine learning models need to be continually updated or corrected to ensure that the prediction accuracy remains consistently high. In this study, we consider scenarios where developers should be careful to change the prediction results by the model correction, such as when the model is part of a complex system or software. In such scenarios, the developers want to control the specification of the corrections. To achieve this, the developers need to understand which subpopulations of the inputs get inaccurate predictions by the model. Therefore, we propose correction rule mining to acquire a comprehensive list of rules that describe inaccurate subpopulations and how to correct them. We also develop an efficient correction rule mining algorithm that is a combination of frequent itemset mining and a unique pruning technique for correction rules. We observed that the proposed algorithm found various rules which help to collect data insufficiently learned, directly correct model outputs, and analyze concept drift.

In practical machine learning, models are frequently updated, or corrected, to adapt to new datasets. In this study, we pose two challenges to model correction. First, the effects of corrections to the end-users need to be described explicitly, similar to standard software where the corrections are described as release notes. Second, the amount of corrections need to be small so that the corrected models perform similarly to the old models. In this study, we propose the first model correction method for classification models that resolves these two challenges. Our idea is to use an additional decision tree to correct the output of the old models. Thanks to the explainability of decision trees, the corrections are describable to the end-users, which resolves the first challenge. We resolve the second challenge by incorporating the amount of corrections when training the additional decision tree so that the effects of corrections to be small. Experiments on real data confirm the effectiveness of the proposed method compared to existing correction methods.

Evaluating influence spread in social networks is a fundamental procedure to estimate the word-of-mouth effect in viral marketing. There are enormous studies about this topic; however, under the standard stochastic cascade models, the exact computation of influence spread is known to be #P-hard. Thus, the existing studies have used Monte-Carlo simulation-based approximations to avoid exact computation.

UNLABELLED: Omokage search is a service to search the global shape similarity of biological macromolecules and their assemblies, in both the Protein Data Bank (PDB) and Electron Microscopy Data Bank (EMDB). The server compares global shapes of assemblies independent of sequence order and number of subunits. As a search query, the user inputs a structure ID (PDB ID or EMDB ID) or uploads an atomic model or 3D density map to the server. The search is performed usually within 1 min, using one-dimensional profiles (incremental distance rank profiles) to characterize the shapes. Using the gmfit (Gaussian mixture model fitting) program, the found structures are fitted onto the query structure and their superimposed structures are displayed on the Web browser. Our service provides new structural perspectives to life science researchers. AVAILABILITY AND IMPLEMENTATION: Omokage search is freely accessible at http://pdbj.org/omokage/.

We developed a new Web authentication protocol with password-based mutual authentication which prevents various kinds of phishing attacks. This protocol provides a protection of user's passwords against any phishers even if a dictionary attack is employed, and prevents phishers from imitating a false sense of successful authentication to users. The protocol is designed considering interoperability with many recent Web applications which requires many features which current HTTP authentication does not provide. The protocol is proposed as an Internet Draft submitted to IETF, and implemented in both server side (as an Apache extension) and client side (as a Mozilla-based browser and an IE-based one).

In a previous paper we developed an optical three-axis tactile sensor that can acquire normal and shearing forces to be mounted on a robotic finger. Normal and shearing forces applied to the sensing element were detected separately; when we examined the repeatability of the present tactile sensor with 1,000 loading-unloading cycles, the respective error of the normal forces was 2%. In the present paper, the three-axis tactile sensor is mounted on a robotic finger of three degrees of freedom to evaluate it for dexterous hands. A series of three kinds of experiments were performed. First, the robotic hand touches and scans flat specimens to evaluate the sensing ability of the friction coefficient. Second, it detects the contour of parallelepiped and cylindrical objects. Finally, it manipulates a parallelepiped case put on a table by sliding it on the table. Since the present robotic hand was able to perform the above three tasks with appropriate precision, we expected that it would be applicable to dexterous hands in subsequent studies.

This paper presents development of tactile sensing-based control algorithm for humanoid robot finger system with optical three-axis tactile sensor mounted on fingertips. Our aim is to develop an intelligent control system that can recognize stiffness of unknown objects and respond to sudden changes of object’s weight during object manipulation. For this purpose, we developed a novel optical three-axis tactile sensor system based on an optical waveguide transduction method capable of acquiring normal and shearing forces. We proposed a control algorithm in the finger control system based on tactile and slippage sensations, and analyzed real-time grasp synthesis in object manipulation tasks. The control algorithm was designed to control fingertips movements by defining optimum grasp pressure and perform re-push movement when slippage was detected in object manipulation tasks. Verification experiments using humanoid robot fingers were conducted whose results revealed that the finger’s system managed to recognize the stiffness of unknown objects and complied with sudden changes of the object’s weight during object manipulation tasks.

A statistical model, based on extensive experimental data, was established to characterize the urban radio propagation medium in various urban environments. Describing the medium by a linear filter, the peaks of the multipath response were analyzed statistically concerning the distribution of the path strength and the path arrival time. The statistical properties of these quantities depend on the modulation delay time. The resulting model can be used for simulation experiments in order to avoid costly hardware tests of ad hoc systems.