The dental numbering for periapical radiograph based on multiple fuzzy attribute approach proposed here analyzes each individual tooth based on multiple criteria such as area/perimeter and width/height ratios. The classification and numbering in a special dental image called a periapical radiograph is studied without speculative classification in cases of ambiguous objects, so an accurate, assistive result is obtained due to the capability of handling ambiguous teeth. Experiment results in using periapical dental radiograph from the University of Indonesia indicate a total classification accuracy of 82.51%, an average classification rate per input radiograph of 84.29%, a maxilla-mandible identification accuracy from 78 radiographs of 82.05%, and a numbering accuracy from 15 radiographs of 90.47%. It is planned that the proposed classification and numbering be implemented as a submodule for dental-based personal identification now being developed.

The design of the optimal fuzzy fractional-order PID controller is addressed in this work. A multi-objective genetic algorithm is proposed to design rule base and membership functions of the fuzzy logic systems. Three conflicting objective functions in both time and frequency domains have been used in Pareto design of the fuzzy fractional-order PID controller. The simulation results reveal the effectiveness of the proposed method in comparison with the results produced by the fractional-order PID controllers.

In this paper we propose a complex system, involving two control algorithms, to provide a final estimation of Resort Management System (RMS). This distinct RMS quality value depends on some individual appreciations, assigned by customers to basic services. In order to improve the qualities of control actions, we intend to add parametric membership functions of fuzzy sets to the fuzzification part. Another modification considers the newly designed technique of determining some essential estimates in the processing part of control to employ all entry data in the result of final decision.

Original rough set theory deals with precise and complete data, even though real applications frequently contain imperfect information. Missing values are typical imperfect data studied in rough set research. Many ideas have been proposed in the literature to solve the issue of imperfect data, but hardly a single solution is sufficient for multiple types of imperfect data containing imprecision and uncertainty. The paper models some basic relations between objects with respect to an imperfect attribute value using the Dempster-Shafer theory of evidence, and defines uncertain relations between objects with multiple imperfect attribute values by combining basic relations defined in a single attribute. It also proposes new rough set models based on these basic relations and discusses the properties of these models.

Tsallis entropy is a q-parameter extension of Shannon entropy. Based on the Tsallis entropy, we have introduced an entropy maximization method to fuzzy c-means clustering (FCM), and developed a new clustering algorithm using a single-q value. In this article, we propose a multi-q extension of the conventional single-q method. In this method, the qs are assigned individually to each cluster. Each q value is determined so that the membership function fits the corresponding cluster distribution. This is done to improve the accuracy of clustering over that of the conventional single-q method. Experiments are performed on randomly generated numerical data and Fisher’s iris dataset, and it is confirmed that the proposed method improves the accuracy of clustering and is superior to the conventional single-q method. If the parameters introduced in the proposed method can be optimized, it is expected that the clusters in data distributions that are composed of clusters of various sizes can be determined more accurately.

This paper proposes an application that analyzes and displays electrocardiograms (ECG; electrical activity of the heart over time) and plethysmograms (PTG; pulse waves produced by the heart pumping blood to the periphery) measured simultaneously. Recently in developed countries, chronic conditions typified by lifestyle-related diseases have become the leading cause of death. Simplified monitoring of the condition can be an effective approach to disease prevention and health promotion. We have focused on autonomic nervous system activity (ANSA) because it responds to stress as well as to changes in dietary patterns, and is correlated with hypertension, the source of some diseases, such as coronary disease. In this paper, we deal with both ECGs and PTGs as part of the biological data that reflects ANSA. The proposed application enables doctors to seamlessly negotiate analyzed waveforms and index charts of ECGs and PTGs in sync with each other. It also helps them comprehend the transition of ANSA. It offers a user interface (UI) that enables doctors to observe the two measures and the relationship between them for a quick assessment of ANSA; the sonification function of the ECG indices is implemented for providing the multi-modality of the UI. An experiment was conducted to confirm the feasibility of the analysis method of the application.

Cognitive infocommunications (CogInfoCom) investigates connections between the cognitive sciences and different areas of infocommunications. CogInfoCom also focuses on engineering application fields integrating related scientific areas and results.

Cognitive infocommunications systems involve hardware and software components that collect and store information and enable users to interact with this information. Besides communication security, considerations include the amount of stored information, which may be huge. This means that there is a need for algorithms and solutions that store and process data effectively. The CogInfoCom field presents a number of motivational challenges requiring active deep research, implementation, integration and measurement.

This special issue focuses on the Cognitive Mobile Applications and Services track of the 3rd IEEE International Conference on Cognitive Infocommunications (CogInfoCom’12). Mobile phones and tablets are now everyday tools that enable users to easily connect to the Internet, download social content, find interesting places, etc. Mobile technology has become one of the most important fields in the IT industry just as Web technology was 10-15 years ago. Mobile phones and tablets use sensors and interfaces like accelerometers, cameras, GPS, and thermometers that monitor and enable easier interaction with the real world. Agents hosted by mobile devices that learn from sensor-originated information also support individual applications and complex systems.

This special issue focuses on the cognitive capabilities of mobile phones, the various agents that mobile devices host, and how they can be applied efficiently in applications and services including social aspects of mobile solutions. Papers from the conference cover mobile controlled environments, mobile-supported learning, augmented reality, energy efficiency and communication techniques.

We thank the authors for submitting their papers to CogInfoCom as a venue for presenting their findings. We are also grateful to program committee members and reviewers for their efforts in making the conference and the special issue possible. We feel that these papers will provide readers with interesting and valuable results from the field of cognitive infocommunications.

Web analytics are used to retrieve anonymous information about users. We focus here on websites that support mobile clients. This information is important from the perspective of business analysis as web analytics help in making appropriate design decisions. Popular web sites may handle several million page views a day, so poor system design – even that related only to collecting statistics on user behavior – may produce performance bottlenecks or even system failures. This paper presents measurements based on a user-data database for a large mobile supported website and a model used when designing such sites.

Our paper shows how the evolution of HCI devices progresses as a mobile learning tool. Mobile devices provide interesting applications for cognitive infocommunication. Our principal objective is to assist in developing educational games on these devices. Working with different educational institutes, we designed a flexible biofeedback-controlled self-rewarding framework. Several promising approaches and methods are proposed outside the box of educational games in this paper. The attention of players is regulated by changing rewards. We show both how educational games can be improved and how adaptive entertainment games may be developed in the near future.

Decentralized algorithms are often used in the cooperative robotics field, especially by large swarm systems. We present a distributed algorithm for a problem in which a group of autonomous mobile robots must surround a given target. These robots are oblivious, i.e., they have no memory of the past. They use only local sensing and need no dedicated communication among themselves. We introduce, then solve the problem in which the group of autonomous mobile robots must surround a given target – we call it the “discrete multiorbit target surrounding problem” (DMTSP). We evaluate our solution using simulation and prove that our solution invariably ensures that robots enclose the target in finite time.

With the many changes in mobile phone use, it is now common for users to connect to the Internet and share social and multimedia data, and peer-to-peer technology remains one of the most efficient solutions to content sharing. We analysed the lifecycle of content shared using the BitTorrent network, focusing on torrents retrieved by mobile phone clients using our MobTorrent application. MobTorrent, a complete BitTorrent client for feature phones, enables anonymous usage statistics to be collected. Based on statistics collected over the last three years, we analyze how mobile BitTorrent clients are being used. We discuss the success of individual sessions by additionally measuring peer connection download and success ratio statistics. This research can be considered as a pioneer work in the field of mobile content sharing solutions.

Rheumatoid arthritis (RA) is a chronic, systemic disorder that may affect many tissues and organs, but principally attacks flexible joints. We examined the effect of eurhythmy on the development of young adult female. 1 young adult female participated in eurhythmy. We analyze walking two times a (it means two full body analyses each time – with and without staff at the same time).

This paper proposes a method for classifying informative reviews based on personal values. Reviews of an item are useful for a user who is considering purchasing it. However, it is difficult for readers to find informative reviews from vast amount of reviews because of existence of too many uninformative reviews. This paper supposes that the value of a review is affected by reader-dependent and independent factors. Typical uninformative reviews in terms of reader-independent factor are copy-and-paste reviews, which do not provide any readers with useful information for their decision-making. On the other hand, it is supposed different readers regard different reviews as informative, which is affected by their personal values. This paper focuses on such a reader-dependent factor, and proposes a methods for classifying informative reviews based on reader’s personal value. Experiments are conducted using actual review data provided by Rakuten Inc., of which the results show about 0.7 of average accuracy is achieved. Furthermore, it is also shown proposed method can model judging criteria common to those who have similar personal values.

Nowadays, an increasingly large amount of information exists on the web. Therefore, a method is needed that enables us to find necessary information quickly because this is becoming increasingly difficult for users. To solve this problem, information retrieval systems like Google and recommendation systems like that on Amazon are used. In this paper, we focus on information retrieval systems. These retrieval systems require index terms, which affect the precision of retrieval. Two methods generally decide index terms. One is analyzing a text using natural language processing and deciding index terms using varying amounts of statistics. The other is someone choosing document keywords as index terms. However, the latter method requires too much time and effort and becomes more impractical as information grows. Therefore, we propose the Nikkei annotator system, which is based on the model of the human brain and learns patterns of past keyword annotation and automatically outputs keywords that users prefer. The purposes of the proposed method are automating manual keyword annotation and achieving high speed and high accuracy keyword annotation. Experimental results showed that the proposed method is more accurate than TFIDF and Naive Bayes in P@5 and P@10. Moreover, these results also showed that the proposed method could annotate about 19 times faster than Naive Bayes.

Data interpretation of electric logging can be performed using self-learning systems such as artificial neural networks (ANNs). Preliminary research shows that by using ANN we can achieve 52–73% of coincidence of interpretable data and experimental results. Therefore, it is necessary to analyze the possibility of using other classification algorithms, and that of using several classification algorithms simultaneously through a unified system (referred to as an integrator. These algorithms may improve the quality of recognition of individual species. The problem of developing a recognition system that combines several classification algorithms, also known as the integrator, is formulated here. A simple algorithm is developed for the learning and recognition of an integrator for the post processing stage; this enhances the recognition accuracy by 1–3%.

Sharing traveling experience and photos on Social Network Service or Web albums is more and more popular recently. Good sightseeing photos in specific situation such as sunset and spring season can impress tourists well, and be clues for them to consider where and when to visit for sightseeing. Regarding situations to be identified, this paper focuses on season. Compared with situations relating with weather and time of day (e.g., sunrise/sunset), whether or not different seasons have different scenery depends on sightseeing spots. Therefore, classifying sightseeing spots into season-dependent/independent is required as preprocessing for season-based classification of sightseeing photos. This paper proposes a hybrid approach for identifying season-dependent sightseeing spots, of which the first phase applies machine learning with statistical features of sightseeing photos obtained from metadata. In order to improve precision, the second phase applies color-based classification to spots identified as season-dependent in the first phase. The experimental results show the effectiveness of the proposed method.

We try to improve discontinuous output change in SpikeProp. The problem is that small variants in input cause significant change in output. We first show that peaks in activity cause the problem. We then propose reducing the height of peaks by weight decay. Through experiments, we conclude that the square type of weight decay is suitable for solving the problem, because it reduces to more than half the patterns that cause discontinuous output change around them.

Most semi-supervised learning methods are based on extending existing supervised or unsupervised techniques by incorporating additional information from unlabeled or labeled data. Unlabeled instances help in learning statistical models that fully describe the global property of our data, whereas labeled instances make learned knowledge more human-interpretable. In this paper we present a novel way of extending conventional non-negative matrix factorization (NMF) and probabilistic latent semantic analysis (pLSA) to semi-supervised versions by incorporating label information for learning semantics. The proposed algorithm consists of two steps, first acquiring prior bases representing some classes from labeled data and second utilizing them to guide the learning of final bases that are semantically interpretable.

This paper presents a mass-spring model applied to the manipulation of an elastic deformable object for home service robot application. A system is also proposed that is used to fold a piece of rectangular cloth from a specific initial condition using a robot. The cloth is modeled as a three-dimensional object in a two-dimensional quadrangular mesh based on a mass-spring system, and its state is estimated using an explicit integration scheme that computes the particle position as a function of the internal and external forces acting on the elastic deformable object. The current state of the elastic deformable object under robot manipulation is tracked based on the trajectory of the mass points in the mass-spring system model in a self-developed simulator, which integrates a mass-spring model and a five-degree-of-freedom articulated robotic arm. To test the reliability of the model, the simulator is used to predict the best possible paths for using the robotic arm to fold a rectangular cloth into two. In the test, the state of the object is derived from the model and then compared with the results of a practical experiment. Based on the test, the error is found to be generally acceptable. Thus, this model can be used as an estimator for the vision-based tracking of the state of an elastic deformable object for manipulation by home service robots.

In this paper, we focus on fuzzy random multiobjective linear programming problems with variance covariance matrices through fractile optimization, and propose an interactive decision making method to obtain a satisfactory solution. In the proposed method, it is assumed that the decision maker has fuzzy goals for not only permissible probability levels but also the corresponding objective functions. Such fuzzy goals are quantified by eliciting the corresponding membership functions. Using the fuzzy decision, such two kinds of membership functions are integrated, and D_f-Pareto optimal solution concept is defined in the integrated membership space. By using the bisection method and the convex programming technique, a satisfactory solution is obtained from among a D_f-Pareto optimal solution set through the interaction with the decision maker.

Niche construction is a process whereby organisms that modify their own or others’ niches through their ecological activities. Recent studies have revealed that changes in social structures of interactions caused by social niche construction of individuals can affect seriously the evolution of cooperation. However, such a social niche also could be changed indirectly by a modification of their physical environment. Our purpose is to clarify the coevolution of cooperative behavior and physically niche-constructing behavior that modifies social niche indirectly. For this purpose, we constructed an evolutionary model in which each individual has not only a strategy for a spatial Prisoner’s Dilemma but also has traits for a niche-constructing behavior for modifying its physical environment that can limit social interactions between neighboring individuals. By conducting evolutionary experiments, we show that a cyclic coevolution between cooperative behavior and niche-constructing behavior occurred in the situation with no or low degree of ecological inheritance, in which the constructed niche could not be inherited in succeeding generations at all. Conversely, when the degree of ecological inheritance was high, the evolution of cooperation was promoted by the emerged environmental structure constructed by the evolved niche-constructing behavior. We also show that the condition for each scenario to occur depends on the settings of the payoff parameters as well as the degree of ecological inheritance.

We apply a genetic programming approach to learning of glycan motifs by using tag tree patterns and various fitness functions. Tag tree patterns obtained from some glycan data show characteristic tree structures. We examine the effects of using various fitness functions on GP processes and obtained glycan motifs. We also show that our method is applicable to tree structured data other than glycan data.

The Nash demand game (NDG) has been at the center of attention when explaining moral norms of distributive justice on the basis of the game theory. This paper describes the demand-intensity game (D-I game), which adds an “intensity” dimension to NDG in order to discuss various scenarios for the evolution of norms concerning distributive justice, while keeping such simplicity that it can be analyzed by the concepts and tools of the game theory. We perform an ESS analysis and evolutionary simulations, followed by the analysis of replicator dynamics. It is shown that the three norms emerge: the one claiming an equal distribution (Egalitarianism), the one claiming the full amount (Libertarianism), and, as the special case of Libertarianism, the one claiming the full amount but conceding the resource in conflict (Wimpylibertarianism). The evolution of these norms strongly depends on the conflict cost parameter. Egalitarianism emerges with a larger conflict cost while Libertarianism with a smaller cost. Wimpy libertarianism emerges with a relatively larger conflict cost in libertarianism. The simulation results show that there are three types of evolutionary scenarios in general. We see in most of the trials the population straightforwardly converges to Libertarianism or Egalitarianism. It is also shown that, in some range of the conflict cost, the population nearly converges to Egalitarianism, which is followed by the convergence to Libertarianism. It is shown that this evolutionary transition depends on the quasi stability of Egalitarianism.

Onomatopoeia has been widely used recently in food reviews about food or restaurants. In this paper, we propose and evaluate a method to automatically extract onomatopoeia including unknown ones from food reviews sites. From the evaluation result, we found that it is able to extract onomatopoeia for specific foods with more than 46% precision; the method found 18 new unknown food-related onomatopoeias, i.e., not registered in an existing onomatopoeia dictionary, and in 62 extracted onomatopoeias. In addition, we propose a system that can present the user with a list of onomatopoeia specific to a restaurant she/he is interested in. The evaluation results indicate that an intuitive restaurant search can be done via a list of onomatopoeia, and that they are helpful for selecting food or restaurants.

The Chinese market is indispensable for international automobile enterprises and they are expanding their investment in this market accordingly. To escalate their market share in China, automobile manufacturers and independent automotive enterprises have implemented a series of management strategies. Consequently, competition in China is becoming increasingly intense. Conversely, Chinese automobile enterprises have no international brand recognition. In this paper, an independent automobile enterprise, Chery Automobile Co. Ltd., is selected as a case study and examined using the SWOT (Strengths, Weaknesses, Opportunities and Threats) method. Moreover, we analyzed the strengths and weaknesses of the company’s internal environment using a fuzzy VRIO (Value, Rarity, Immutability and Organization) method. Applying the fuzzy theory to an analysis of the management environment can facilitate more effective strategy formulations. It is expected that the application of fuzzy theory to management methods will contribute to the future development of the Chinese automobile industry. The competitive advantages to Chery are illustrated by the fuzzy VRIO analysis.

We consider the design procedure for a single-phase PWM DC-AC inverter using a particle swarm optimization algorithm. The switching operation is the most important component of the single-phase PWM DC-AC inverter. The PSO algorithm optimizes the switching angle effectively. The design procedure of the switching angle evaluates total harmonic distortion and the effective value of output. The proposed evaluation function restricts the scope to evaluating harmonic components. Based on numerical simulation results, we confirmed that the performance of the proposed design procedure was improved compared to the conventional sinusoidal PWM procedure. We develop an implementation circuit for our PWM DC-AC inverter. By using the implemented circuit, we confirmed that results for implementation circuits are consistent with results for numerical simulations, indicating that the proposed algorithm exhibits better performance than the conventional sinusoidal PWM DC-AC inverter.

This paper explores a performance of first-order configuration prediction for redundant manipulators based on avoidance manipulability in order to achieve an on-line control of trajectory tracking and obstacle avoidance for redundant manipulators. In the trajectory tracking process, manipulator is required to keep a configuration with maximal avoidance manipulability in real time. Predictive control in this paper uses manipulators’ future configurations to control current configuration aiming at completing tasks of trajectory tracking and obstacle avoidance on-line and simultaneously with higher avoidance manipulability. We compare Multi-Preview Control with predictive control using redundant manipulator, and show the results through simulations. The effectiveness of predictive control using first-order configuration prediction is also validated in the case of not only straight target trajectory but also curve target trajectory. In addition, an influence of measurement noise on manipulator’s joint angle is newly considered.

A pipe inspection robot, called a boiler header inspection robot (BHIR), is presented in this paper. The BHIR was designed specifically to inspect the inner surfaces of horizontal boiler header pipes in a thermal power plant in Malaysia that is owned by Tenaga Nasional Berhad (TNB). The main challenge was the geometry of a boiler header pipe: the entry diameter is significantly smaller than the diameter of the main pipe body. Currently, there are two versions of the BHIR: 1) the first version, BHIR-I, which was developed for use in manual inspections by carrying a borescope camera inside a boiler header pipe, and 2) the second version, BHIR-II, which has an on-board visual inspection system that can inspect pipes and acquire images independently. The robot was designed to be able to navigate through the pipe geometry. A unique redundant localization system that uses an accelerometer and encoder sensor was developed to ensure that the robot knows the location of the images taken and its own position inside the boiler header pipe. This paper discusses the prototype development, the localization system and site testing conducted to validate the prototype. Based on the test results, the BHIR prototype with redundant localization was proven to be successful.