Search

Two line-based fracture detection schemes are developed and discussed, namely Standard line-based fracture detection and Adaptive Differential Parameter Optimized (ADPO) line-based fracture detection. The purpose of the two line-based fracture detection schemes is to detect fractured lines from X-ray images using extracted features based on recognised patterns to differentiate fractured lines from non-fractured lines. The schemes reduce the number of images required for training, as the training is performed line-wise. The difference between the two schemes is the detection of lines. The ADPO scheme optimizes the parameters of the Probabilistic Hough Transform, such that granule lines within the fractured regions are detected. The lines are given in the form of points, (x, y), which includes the starting and ending points. Based on the given line points, 13 features are extracted from each line as a summary of line information. These features are used for fracture and non-fracture classification of the detected lines. The classification is carried out by the Artificial Neural Network (ANN). The Standard Scheme is capable of achieving an average accuracy of 71.57%, whereas the ADPO scheme achieved an average accuracy of 72.89%. The ADPO scheme is opted for over the Standard scheme, however it can be further improved with contour fracture detection.

Dengue virus detection using blood smear with staining method known as immunocytochemistry streptavidin biotin peroxidase complex has early detection problem caused by the low in number of leukocyte in early day of infection. In order to help the detection of virus infection, this research develop automated system to count and classify infected leukocyte from the microscopic image using image histogram based support vector machine. Image processing is for the detection of the cells by using Gram-Schmidt orthogonalization for converting image into grayscale high contrast grayscale image, median filter for image smoothing, Otsu threshold for image segmentation, image morphology and circularity filter for cleaning up unwanted noise after segmentation. Furthermore, support vector machine for the infected cell classification using image histogram of the cells as feature vector. The result of the research is the image histogram based suport vector machine can classify the infected leukocyte with 83.94% accuracy.

Process modeling as one of the critical Business Process Management (BPM) disciplines is recognized as a key anchor to digital transformation (DT) efforts currently underway in most enterprises. While enterprises are transforming digitally, the practice of process modeling is also changing with little guidance on key considerations for realizing success process modeling. The focus of the paper was to determine key antecedents for realizing effective processing modeling during DT projects. A case study of a bank transforming its Customer Relationship Management (CRM) was used as a basis to “tease out” key factors critical for successful DT. A number of inferences emanate from the findings of this paper. The first is linked to the increasingly knowledge-based orientation and digitalization of our society that requires a re-think of how current organizations are structured and modelled. The notion of “Digitalization of Project Management” also emerged to undergird current transformations in project management, which affects how process modelling is currently practiced. Secondly, the implications of such digital transitions in process modeling is that the process of organizational modeling and structuring is encouraging more “Knowledge-Enabled Participation”, with its emphasis on expertise, team structure and competence of project participants. The last inference conflates the factors of “DT Evaluation” and “DT Modeling” that emerged from this study to make the following claim: that the process of organizational transformation will increasingly be “machine-based”, with process modeling and evaluation becoming predominantly digitalized. Therefore, process modeling and its foundational disciplines (such as project management and business process management) will transform, with an orientation elevating older terminologies such as automation and data-intensive processing; with organizational strategy intricately linked to process modeling as its anchor.

Music is known to be a powerful elicitor of emotions. Here, we examined the possibility of decoding musicinduced experienced emotions – affective responses induced in the listener by music stimuli – using functional magnetic resonance imaging (fMRI) data collected while participants listened to various movie soundtrack excerpts. Using a machine learning based classification framework, preliminary results indicate that it is possible to, under certain conditions, decode the arousal (High/Low) and valence (Positive/Negative) of the emotional state experienced during listening. Future work will be aimed at improving methodological issues in order to establish whether these results extend to larger populations and more general types of music stimuli.

One application of brain-computer interface (BCI) is for entertainment. BCI games have potential extensibility in combination with virtual reality environment. In our previous study, we have proposed a BCI game system composed of a simple EEG recorder, which detects beta/alpha ratio, a smart tablet, a PC, and an immersive head mounted display. In this study, we further proposed a hands-on game by combining the BCI game system additionally with a wearable gesture interface, which detects electromyography. We found that addition of the wearable gesture interface increase users' feeling of presence and fun, but decreased the beta/alpha ratio.

Our research focuses privacy problem on data utilization of the connected car. In this paper, we discuss the user's acceptance of the privacy setting for the data utilization on the connected car based on our previous qualitative survey. That quantitative survey was based on the hypotheses that three factors “Consent form”, “On/Off function”, and “Style of provision” shows strong effectiveness to the privacy setting acceptance of the drivers for the data utilization on the car. In the quantitative survey, scenarios and use-cases based on the three factors had been presented to respondents. As a result of analyzing the answers of the respondents, we display “Consent form” as a more important factor than others. In addition, we show the analysis results of the answers to use-case based questions. The results revealed as the most effective use-case was one strongly related to personal preference

In this paper, we introduce a study on privacy setting acceptance of drivers for data utilization on vehicles, and factors related to privacy setting. This qualitative research is based on the factors extracted from former research on privacy setting acceptance for ICT services. That is conducted through questionnaires and depth interviews on connected car services. As a result, we show acquiring consent for privacy policy on data acquisition and service utilization, on and off switch of service utilization, and information acquisition timing are important factors for privacy setting acceptance. We also discuss specific opinions which are obtained by depth interviews.

In this report, we discuss about a data mining method for multi-modal in-vehicle sensor signals. Though several methods were previously proposed for symbolization of the multi-modal in-vehicle signals, the effectiveness of such method were not discussed in detail. We adopt the Bag-of-System (BoS) technique, a variation of the Bag-of-Features for sensor signals used in motion analysis, and evaluate the effectiveness for several complicated scenarios. According to the requirement of realistic practical data analysis, we extend the BoS technique and evaluate for scenarios such as lane change detection and turning estimation. According to the evaluation of the simple case, three behaviors at the intersections are successfully estimated. However, the technique exhibited lower performance for a complicated behavior such as lane change.

Packet classification has become increasingly complex and important to network equipment intended for future use. A recent trend to achieve complex packet classification is to use software-based methods, which tend to be slower than hardware-based methods. For search, this typically means using ternary content-addressable memory (TCAM) to make classification feasible. However, TCAM is not well-suited to the long (in bits) and sparse rules used for running advanced applications that require complicated classification. We propose a multi-dimension search engine (MDSE) that is optimized for use with long, sparse rules, and we propose a multi-dimensional TCAM scheme, which is an MDSE constructed to operate on TCAM. Through fine-grained simulations with real traffic, we show that our proposed search engine can reduce the power consumed by network equipment by about 85%.

Microwave Doppler sensors commonly used in automatic-door systems have been used in a rover navigation system. A collimated microwave beam with an angular width of ±3° at a frequency of 24 GHz was emitted from a sensor (A) on a dish antenna 30 cm in diameter. Another sensor (B), which works as a detector, was installed on the rover. The rover was programmed to make a right turn when the microwave signal was above a specified level and to make a left turn when the signal was below that level. In this study, we fabricated the third prototype rover. To confirm the effectiveness of the proposed method, we performed the experiments on the strength distribution of the microwave beam and on the navigation control with the fabricated rover. Finally, we had a questionnaire for the student who collaborated with this study to investigate how the education effects for the student were.

Microwave Doppler sensors commonly used in automatic-door systems have been used in a rover navigation system. A collimated microwave beam with an angular width of ±3° at a frequency of 24 GHz was emitted from a sensor (A) on a dish antenna 30 cm in diameter. Another sensor (B), which works as a detector, was installed on the rover. The rover was programmed to make a right turn when the microwave signal was above a specified level and to make a left turn when the signal was than that level. In this study, we fabricated the third prototype rover. To confirm the effectiveness of the proposed method, we performed the experiments on the strength distribution of the microwave beam, and on the navigation control with the fabricated rover.

We evaluate the damage on living cells induced by electron beam irradiation. Cell viability is observed with a fluorescence microscope. Electron beam induced damage is evaluated by the comparison of fluorescence images obtained before and after the electron beam irradiation. After electron beam irradiation, a bleb related to cell injury was observed and cell viability signal was decreased on the irradiated cell.

Cell culture on a silicon nitride membrane is required for atmospheric scanning electron microscopy, electron beam excitation-assisted optical microscopy, and various biological sensors. Cell adhesion to a silicon nitride membrane is weak, and the proliferation potential is also limited. Therefore, we considered that the adhesion force and proliferation potential of cultured cells might be increased by controlling the surface hy-drophilicity. In this study, we covalently coupled carboxyl groups on silicon nitride membranes to increase the hydrophilicity. We measured contact angles of water droplets on silicon nitride membrane surfaces to evaluate the hydrophilicity. Moreover, we successfully cultured HeLa cells on coated membranes. Cell migration and confluence were observed on the coated silicon nitride film.

In this report, we have proposed a new data mining method to analyze vehicles' temporal behaviors. The Bag-of-Systems (BoS) representation was adopted to analyze the temporal behavior signals. The BoS representation was originally used for analyzing motion data from video image. We have extended the model of dynamical systems to analyze vehicles' temporal behaviors of both travel direction and rotational direction. By using this method, a symbol sequence was obtained for each trip. Therefore we could apply various data mining method to the obtained sequences. As for the first trial, a clustering method was applied to the sequences and characteristic segments to know the events happened on the vehicles were successfully found.

In this study, fist, we conducted a study on the navigation control for a rover using microwave Doppler sensors. Microwave Doppler sensors commonly used in automatic-door systems have been used in a rover navigation system. A collimated microwave beam with an angular width of ±3° at a frequency of 24 GHz was emitted from a sensor (A) on a dish antenna 30 cm in diameter. Another sensor (B), which works as a detector, was installed on the rover. The rover was programmed to make a right turn when the microwave signal was above a specified level and to make a left turn when the signal was than that level. The rover started from a point 70 m away and approached to within 1.5 m of sensor A. This navigation method is useful when GPS is not usable. Second, we proposed a method to avoid irregular surfaces on a ground because the prototype rover we have previously developed could not be navigated owing to the cut of the microwave beam by large irregularity of ground surfaces. In this study, second prototype rover with a function of avoiding the irregular ground surfaces was fabricated and we confirmed the effectiveness of the proposed method through some experiments.

Microwave Doppler sensors commonly used in automatic-door systems have been used in a rover navigation system. A collimated microwave beam with an angular width of ±3° at a frequency of 24 GHz was emitted from a sensor (A) on a dish antenna 30 cm in diameter. Another sensor (B), which works as a detector, was installed on the rover. The rover was programmed to make a right turn when the microwave signal was above a specified level and to make a left turn when the signal was than that level. The rover started from a point 70 m away and approached to within 1.5 m of sensor A in 4-5 min. This navigation method is useful when GPS is not usable.

We propose a proactive route recommendation system based on Cyber-Physical system for vehicles. The system is capable of acquiring and analyzing data obtained from the automobile and the Internet. The system consists of two major technologies, prediction algorithms to estimate the driver's destination and route beforehand, and linkage of cyber information (driving events extracted from the Internet) towards the driver's estimated route. The system combines the two data in order to provide substitute routes information for evading driving events. We have developed prediction algorithms and information linking methods, and conducted evaluation with data obtained from drivers, also implemented a prototype application to validate the recommended routes.

Analysis of driving skill/driver state can be used in building driver support and infotainment systems that can be adapted to individual needs of a driver. In this paper we present a machine learning approach to analyzing driving maneuver skills of a driver that covers both longitudinal and lateral controls. The concept is to learn a driver model from sensor data that are related to driving environment, driving behavior and vehicle response. Once the model is built, driving skills of an unknown run can be classified automatically. In this paper, we demonstrate the feasibility of the proposed method for driving skill analysis based on a driving simulator experiment in a curve driving scene for both the full curve and curve segmented cases.

Nowadays, car navigation systems are widely used in cars to aid drivers by providing directions to a destination. However, these systems do not always recommend a route that perfectly matches the driver's intent. Even when drivers intentionally select a route that is different from the recommended one, the system leads them back to the original route. Such recommendations do not adequately reflect the driver's intent. This study proposes a route recommendation method for a car navigation system that estimates the driver's intent and rerecommends a route that matches this intent when the driver deviates from the originally recommended route. We developed a simulator based on the proposed method and used it to experimentally verify the effectiveness of the proposed method.

In-vehicle information provision services have started according to the progress of data communication infrastructure surrounding vehicles. In such information services, a large amount of data related to vehicles and drivers has been accumulated to the data-center and also been analyzed to provide proper information to drivers. Towards such a technical trends surrounding vehicles, a cyber physical system for vehicle application is proposed here. In the proposed system, expected continuous spiral information flow for vehicles and drivers is described. In the data-center, accumulated information has been analyzed by intelligent information processing of data-mining, then finally extracted information has been provided to drivers through human machine interface. According to the progress of the information processing technologies in the data-center, several potential application are introduced mainly based on personal adaptation, big data analysis and web mining.

Car navigation systems, which are a part of technologies of Intelligent Transportation System (ITS), support drivers in driving efficiently by showing the shortest routes and some driving information such as that related to traffic jams and weather reports, that are collected from physical sensors and news media. This paper presents a proposal of a method to extract real-time driving information using social media as a type of 'social sensor'. This is a brand-new approach to acquiring valuable information for drivers from social media. Our method is useful to provide driving information in countries where current ITS deployment is poor. It also provides drivers detailed information related to the current traffic situation. Our research comprises three parts. First, we extract driving information from social media using text-based classification methods. Second, because geographical coordinates are necessary to note where the driving information had occurred, we incorporate a method to transform geographically related terms into geographical coordinates. Finally, we develop a system to provide information about important events for drivers and to evaluate results of event extraction through comparison with information available from current media sources commonly found in most cars. Our proposed system can collect tweets referring to heavy traffic from Twitter with about 0.87 precision and can extract location information from those tweets with 0.85 precision.

We have developed an electron beam excitation assisted near-field scanning optical microscope and demonstrated resolution greater than 50 nm. The microscope has a few tens nanometer spatial resolution laterally and makes it possible to observe dynamic behaviors of living biological specimens in various surroundings such as air or liquids. In the microscope, a light source in a few nanometers size is excited by focused electron beam in a luminescent film. Scan speed of nanometric light source is faster than that of the small aperture in conventional near-field scanning optical microscopes. The optical near-field microscope enables to observe optical constants such as absorption, refractive index, polarization properties, and its dynamic behaviors in nanometer scale. The developed microscope opens new microscopy applications to in nano-technology and nano-science. We also present direct excitation of fluorescented labelling cells.

We propose a passive keyless entry system which applies intrabody communication and updating scheme. Recently authentication vulnerability of the system has been reported. And most of attacks eavesdrop on authentication to extract the shared secret. The passive keyless entry system must be safe at least the life time of the vehicle. Our system uses intrabody communication instead of the wireless communication against eavesdropping. Furthermore in case the shared secret is extracted, our system updates the shared secret frequently. In this paper we describe the system design and the demo system.

In this work a RF component design library has been developed for high performance 6-layered PCBs using a new plating technology. The design library consists of scalable models that are fitted on measurements. It is shown that the high performance PCB exhibits a better transmission line RF performance and also higher Q values for integrated inductors.

Doppler frequency up conversion using optically generated electron-hole plasma in a planar transmission line has been investigated as a potential means for generating high power terahertz waves. Experiments performed at millimeter wavelengths have clearly proved that the Doppler frequency conversion with a frequency up conversion ratio of more than five can be achieved in a slotline with an optically excited silicon substrate.

Using functional magnetic resonance imaging, we examined whether distinct activity patterns are elicited by natural and unnatural visual stimuli. Stimuli were black and white pictures portraying various scenes (e.g., cities, country fields); natural pictures were unaltered, while unnatural pictures were produced by reversing their contrast curves (negative images). Low-contrast pictures were used in tandem to find contrast-sensitive areas in the contrast curves. During scanning, participants performed a simple discrimination task; brain imaging results revealed distinct activity patterns depending on stimulus type. When subjects viewed natural pictures, activity was greater in the angular gyrus and precuneus. In contrast, when viewing unnatural pictures, activity was greater in the fusiform gyrus, inferior temporal cortex, middle occipital cortex, and inferior frontal operculum. These findings indicate that the experience of perceiving visual stimuli as natural or unnatural might be subserved by cortical networks other than those known to be involved in the low-level processing of visual information.

The performance of the helicopters has improved remarkably in recent years. For some helicopters, high mobility is demanded because it sometimes requires extreme movement ability. The purpose of this paper is to apply the technique generally used for trajectory optimization of a fixed wing airplane to analysis of the helicopter mobility. We formulated the two dimensional minimum time vertical turn of a helicopter as the parameter optimization problem and analyzed numerically by using the technique of non-linear programming and show the most suitable orbit and variables. The non-linear programming is quite useful for analysis of optimal problems. The calculation method is the sequential quadratic programming that is well-known method for non-linear programming. The results show the characteristics of the helicopter reasonably.