A new method for creating a chain diagram of events that occur during disasters by extracting causal knowledge from Japanese newspaper articles and designing a causal network is proposed herein. Machine learning discriminant models were created for both conventional cue phrases and succession expressions with causation to extract causal sentences. We found that causal sentences can be extracted with a certain degree of accuracy from disaster articles. We were also able to create a causal network using sentences as nodes and links. The chain diagram using our new method extracted events and causal knowledge that were unavailable in a disaster chain diagram designed using conventional methods.

In this paper, we present the design for a decentralized control method comprising a series of local state feedback controllers for a class of linear fractional composite systems. In addition, the corresponding asymptotic stabilization criterion is derived. First, we design the local state feedback controllers for each subsystem of the linear fractional composite system. Then, based on the vector Lyapunov function, we combine these local state feedback controllers into a single decentralized controller through which the asymptotic stabilization criterion is proposed for the class of linear fractional composite system. Finally, numerical simulation of a class of linear fractional composite systems is used to verify the accuracy and effectiveness of the decentralized control method.

Capacitors and inductors have been proven to exhibit fractional-order characteristics. Therefore, the establishment of fractional-order models for circuits containing such components is of great significance in practical circuit analysis. This study establishes the impedance models of fractional-order capacitors and inductors based on the Caputo–Fabrizio derivative and performs the analog realization of fractional-order electronic components. The mathematical models of fractional RC, RL, and RLC electrical circuits are deduced and verified via a comparison between the numerical simulation and the corresponding circuit simulation. The electrical characteristics of the fractional circuits are analyzed. This study not only enriches the models of fractional capacitors and inductors, but can also be applied to the description of circuit characteristics to obtain more accurate results.

We propose a method for measuring interdisciplinary research by dividing it into two approaches: interdisciplinary research conducted by individual researchers and interdisciplinary research involving the collaboration of multiple researchers. Using this method, a database of “KAKENHI,” which is a grant-in-aid for scientific research provided by the Japan Society for the Promotion of Science (JSPS), is employed to measure interdisciplinary research from the perspective of the two research approaches, and the features of interdisciplinary research in KAKENHI are analyzed. The analysis results indicate the following: (1) the number of collaborative interdisciplinary research projects is larger than the number of individual interdisciplinary research projects, (2) the number of interdisciplinary research projects for each field and for each combination of fields differs among fields, and (3) the relationship between the numbers of interdisciplinary research projects in the two fields is asymmetric with regard to the main- and sub-fields of interdisciplinary research. As the proposed measurement method is capable of quantitatively measuring interdisciplinarity between fields and their research organizations, it will be useful for decision-makers in science and technology policy and strategy.

Based on a single-phase photovoltaic grid-connected inverter, a control strategy combining traditional proportional–integral–derivative (PID) control and a dynamic optimal control algorithm with a fuzzy neural network was proposed to improve the dynamic characteristics of grid-connected inverter systems effectively. A fuzzy inference rule was established after analyzing the proportional, integral, and differential coefficients of the PID controller. A fuzzy neural network was applied to adjust the parameters of the PID controller automatically. Accordingly, the proposed dynamic optimization algorithm was deduced in theory. The simulation and experimental results showed that the method was effective in making the system more robust to external disruption owing to its excellent steady-state adaptivity and self-learning ability.

Although the Takagi–Sugeno fuzzy model is effective for representing the dynamics of a plant to be controlled, two main questions arise when using it just as other models: 1) how to deal with the gap, which is referred to as uncertainty in this study, between the model and the concerned plant, and how to estimate the state information when it cannot be obtained directly, especially with the existence of uncertainty; 2) how to design a controller that guarantees a stable control system where only the estimated state is available and an uncertainty exists. While the existing studies cannot effectively observe the state and the resulting control systems can only be managed to be uniformly stable, this study first presents a state observer capable of precisely estimating the state regardless of the existence of uncertainty. Then, based on the state observer, an uncertainty observer is derived, which can track the trajectory of uncertainty whenever it occurs in a real system. Finally, a controller based on both observers is presented, which guarantees the asymptotic stability of the resulting control system.

Entity disambiguation is extremely important in knowledge construction. The word representation model ignores the influence of the ordering between words on the sentence or text information. Thus, we propose a domain entity disambiguation method that fuses the doc2vec and LDA topic models. In this study, the doc2vec document is used to indicate that the model obtains the vector form of the entity reference item and the candidate entity from the domain corpus and knowledge base, respectively. Moreover, the context similarity and category referential similarity calculations are performed based on the knowledge base of the upper and lower relation domains that are constructed. The LDA topic model and doc2vec model are used to obtain word expressions with different meanings of polysemic words. We use the k-means algorithm to cluster the word vectors under different topics to obtain the topic domain keywords of the text, and perform the similarity calculations under the domain keywords of the different topics. Finally, the similarities of the three feature types are merged and the candidate entity with the highest similarity degree is used as the final target entity. The experimental results demonstrate that the proposed method outperforms the existing model, which proves its feasibility and effectiveness.

In recent years, many systems have been developed to embed deep learning in robots. Some use multimodal information to achieve higher accuracy. In this paper, we highlight three aspects of such systems: cost, robustness, and system optimization. First, because the optimization of large architectures using real environments is computationally expensive, developing such architectures is difficult. Second, in a real-world environment, noise, such as changes in lighting, is often contained in the input. Thus, the architecture should be robust against noise. Finally, it can be difficult to coordinate a system composed of individually optimized modules; thus, the system is better optimized as one architecture. To address these aspects, a simple and highly robust architecture, namely memorizing and associating converted multimodal signal architecture (MACMSA), is proposed in this study. Verification experiments are conducted, and the potential of the proposed architecture is discussed. The experimental results show that MACMSA diminishes the effects of noise and obtains substantially higher robustness than a simple autoencoder. MACMSA takes us one step closer to building robots that can truly interact with humans.

Recent advancements in machine learning and communication technologies have enabled new approaches to automated fault diagnosis and detection in industrial systems. Given wide variation in occurrence frequencies of different classes of faults, the class distribution of real-world industrial fault data is usually imbalanced. However, most prior machine learning-based classification methods do not take this imbalance into consideration, and thus tend to be biased toward recognizing the majority classes and result in poor accuracy for minority ones. To solve such problems, we propose a k-means clustering generative adversarial network (KM-GAN)-based fault diagnosis approach able to reduce imbalance in fault data and improve diagnostic accuracy for minority classes. First, we design a new k-means clustering algorithm and GAN-based oversampling method to generate diverse minority-class samples obeying the similar distribution to the original minority data. The k-means clustering algorithm is adopted to divide minority-class samples into k clusters, while a GAN is applied to learn the data distribution of the resulting clusters and generate a given number of minority-class samples as a supplement to the original dataset. Then, we construct a deep neural network (DNN) and deep belief network (DBN)-based heterogeneous ensemble model as a fault classifier to improve generalization, in which DNN and DBN models are trained separately on the resulting dataset, and then the outputs from both are averaged as the final diagnostic result. A series of comparative experiments are conducted to verify the effectiveness of our proposed method, and the experimental results show that our method can improve diagnostic accuracy for minority-class samples.

Although image change detection (ICD) methods provide good detection accuracy for many scenarios, most existing methods rely on place-specific background modeling. The time/space cost for such place-specific models is prohibitive for large-scale scenarios, such as long-term robotic visual simultaneous localization and mapping (SLAM). Therefore, we propose a novel ICD framework that is specifically customized for long-term SLAM. This study is inspired by the multi-map-based SLAM framework, where multiple maps can perform mutual diagnosis and hence do not require any explicit background modeling/model. We extend this multi-map-based diagnosis approach to a more generic single-map-based object-level diagnosis framework (i.e., ICD), where the self-localization module of SLAM, which is the change object indicator, can be used in its original form. Furthermore, we consider map diagnosis on a state-of-the-art deep convolutional neural network (DCN)-based SLAM system (instead of on conventional bag-of-words or landmark-based systems), in which the blackbox nature of the DCN complicates the diagnosis problem. Additionally, we consider a three-dimensional point cloud (PC)-based (instead of typical monocular color image-based) SLAM and adopt a state-of-the-art scan context PC descriptor for map diagnosis for the first time.

The aim of this work is to develop a technology that allows a remote operator of construction machine to feel the situations in a real working site to prevent fall accidents. In tele-operated maneuvering construction machine, it is difficult to recognize the tilt of the vehicle using only images from a camera mounted on the remote vehicle. Therefore, this study focuses on transmitting the feeling of the tilt using a controller with tactile stimulation. A gamepad-type tactile controller that performs palm pressurization is utilized to provide the tactile stimulus. The vehicle’s tilt is expressed by the palm pressure, which changes in corresponding to the vehicle’s pitch and roll angle. This study involves an experiment in which 10 subjects operate a vehicle remotely to climb on a slope. The subjects reported the tilt of the slope felt during the operation. The reported tilt is compared with those obtained by camera images only. The experiment results show that the accuracy of the recognized tilt was improved by 31.7% by utilizing a tactile stimulus when compared with the case involving operation using vision only. A subjective evaluation is performed using a five-point scale questionnaire. The results confirmed that the feeling of tilt, which is difficult to transmit using only video, was improved by 34%. This is an effective technology that transmits the feelings experienced in the remote field in real time. The proposed technology is thus expected to be useful for further development of teleworking technologies.

The demand for fluency in human–computer interaction is on an increase globally; thus, the active localization of the speaker by the machine has become a problem worth exploring. Considering that the stability and accuracy of the single-mode localization method are low, while the multi-mode localization method can utilize the redundancy of information to improve accuracy and anti-interference, a speaker localization method based on voice and image multimodal fusion is proposed. First, the voice localization method based on time differences of arrival (TDOA) in a microphone array and the face detection method based on the AdaBoost algorithm are presented herein. Second, a multimodal fusion method based on spatiotemporal fusion of speech and image is proposed, and it uses a coordinate system converter and frame rate tracker. The proposed method was tested by positioning the speaker stand at 15 different points, and each point was tested 50 times. The experimental results demonstrate that there is a high accuracy when the speaker stands in front of the positioning system within a certain range.