Hiroharu Kawanaka

Obstacle to training SpikeProp networks — Cause of surges in training process —

In this paper, we discuss an obstacle to training in SpikeProp[1], which is a type of supervised learning algorithms for spiking neural networks. In the original publication of SpikeProp, weights with mixed signs are suspected to cause failures of training. We pointed out the cause of it through some experiments. Weights with mixed signs make the dynamics of the units activity twisted, and the twisted dynamics break the assumption that SpikeProp algorithm is based on. Therefore, it causes surges in training processes. They would mean an underlying problem on training processes.

Video Scene Segmentation Using the State Recognition of Blackboard for Blended Learning

We are developing the automatic generating system for video contents with keyword tag in blended learning. The generated lecture movie is too long for students to watch the lecture video on demand. We are considering the segmentation method of the lecture movie by the behavior of a lecturer. In this paper, we present a new segmentation method for one lecture movie to some shots using the behavior of a lecturer such as up-down movement of a blackboard and the erasure of characters on the blackboard. These behaviors are the sign of contents segmentation from the lecturer to students. The system detects the event time of these behaviors, and segments the lecture movie using the event time. We implemented our procedure and evaluated the validity using the lecture movie of some real lectures, and confirm that an accurate segmentation rate is 97%.

Extraction Method of Retinal Border Lines in Optical Coherence Tomography Image by Using Dynamic Contour Model

In the field of ophthalmology, the needs of retina diagnosis using optical coherence tomography (OCT) images have been growing, and the automatic measurement of a retina thickness and its quantitative evaluation are desired for the diagnosis of retinal diseases. Previously, the automatic measurement methods of the retinal thickness have been reported for retinal OCT images. These previous methods can extract the retinal border lines (ILM and RPE) appropriately in most cases of normal OCT image. However these methods caused the tracking error to some OCT images with large noises. In this paper, we propose a new automatic measurement method of a retinal thickness in OCT image. The method employs ODAN (One Directional Active Net) to extract ILM and RPE. ODAN employs a new energy function to extract the retinal border lines exactly and all nodes of ODAN moves only to one direction to minimize the total energy repeatedly. The energy function consists of (1) the conformity characteristics energy of image and (2) the internal strain energy. We confirmed the usefulness of the ODAN by the experimental results for ten OCT images with large noises. We compared the positions of retinal border lines by the proposed method with the positions in a manual trace by ophthalmology specialist. In the comparative result, the proposed method is useful as the basic method for the detection of retinal diseases.

Tendency discovery from incident report map generated by self organizing map and its development

This study discusses a tendency discovery method from medical text data with free format. In this study, we focuses incident reports and proposes a new tendency discovery method for them using self-organizing map. In the first of this paper, we describes the outline of the keyword extraction method from incident reports and coding method to make a map. It is expected that the generated map by the proposed method shows the relation among the incident reports visually and it gives us new knowledge, i.e. trends or features underlaid in reports and difficult to find from each report. The knowledge will be able to help the reduction of incidents in the hospital. Moreover, authors developed a incident report analysis system using the proposed method and discuss the effectiveness of the proposed system. Finally, the paper describes a possibility for the application of SOM to incident reports in the end of this paper.

Keywords Recognition of Handwritten Character String on Whiteboard Using Word Dictionary for e-Learning

We are developing an individual e-learning system using two communication cameras and a pen capture tool on whiteboard for university students. In this research, keywords recognition for the written characters by the lecturer on the whiteboard is important for indexing the scene database. We are considering the handwritten keyword recognition. The whiteboard image captured by the pen capture tool is recognized to character strings and the string corresponds to keywords in a textbook to link to the explanation of the keyword in textbook. One of important problems in our learning system is that the accuracy of handwritten character recognition on whiteboard is not enough for keyword recognition. In this paper, we propose the new matching method of high accuracy keyword recognition using word dictionary and the distance of character recognition. We confirmed the usefulness using word dictionary for handwritten keyword recognition on whiteboard

A Retinal Layer Structure Analysis to Measure the Size of Disease Using Layer Boundaries Detection for Optical Coherence Tomography Images

In the field of ophthalmology, optical coherence tomography (OCT) is rapidly becoming popular in clinical applications to diagnose retinal disease. In this paper, we proposed a new profile analysis to evaluate the size of the retinal disease using the number of layer boundaries. The number is established by a new analysis method of a gray level profile scanned in longitudinal direction for an OCT image. We employed the proposed method for 50 OCT images of normal retina and 50 OCT images of abnormal retina. The experiment result showed that a significant difference was obtained in the significance level at 1%, when we employed Mann-Whitney U method on the standard deviation of the number of layer boundaries for normal and abnormal retinal images group. Therefore, we confirmed that the proposed method becomes one of the indexes to evaluate the size of the retinal disease. In addition, we confirmed that our system can measure the size of abnormal part in horizontal direction using the number of layer boundaries.

Acquisition of fuzzy control rules for a mobile robot using genetic algorithm

Fuzzy controls have been widely used in industry for its high degree of performance in human-computer interactions. DNA coding method, which is one of the coding methods in genetic algorithm, is based on biological DNA and a mechanism of development from the artificial DNA. This method has redundancy and overlapping of genes, and it is suitable for knowledge representation. In this paper, we propose the parallel genetic algorithm using the DNA coding method. This paper applies this method to acquisition of fuzzy control rules with multiple input/output system for a mobile robot. This method can select input variables from many candidates and tune membership functions. The result of simulation shows that the robot can reach the goal quickly and efficiently. Effective fuzzy rules for the mobile robot are acquired by using this method while the length of the chromosomes in the population is automatically adjusted.

A study on feature extraction and disease stage classification for Glioma pathology images

Computer aided diagnosis (CAD) systems are important in obtaining precision medicine and patient driven solutions for various diseases. One of the main brain tumor is the Glioblastoma multiforme (GBM) and histopathological tissue images can provide unique insights into identifying and grading disease stages. In this work, we consider feature extraction and disease stage classification for brain tumor histopathological images using automatic image analysis methods. In particular we utilized automatic nuclei segmentation and labeling for histopathology image data obtained from The Cancer Genome Atlas (TCGA) and check for classification accuracy using support vector machine (SVM), Random Forests (RF). Our results indicate that we obtain classification accuracy 98.9% and 99.6% respectively.

A Study on Nuclei Segmentation, Feature Extraction and Disease Stage Classification for Human Brain Histopathological Images

Computer aided diagnosis (CAD) systems are important in obtaining precision medicine and patient driven solutions for various diseases. One of the main brain tumor is the Glioblastoma multiforme (GBM) and histopathological tissue images can provide unique insights into identifying and grading disease stages. In this study, we consider nuclei segmentation method, feature extraction and disease stage classification for brain tumor histopathological images using automatic image analysis methods. In particular we utilized automatic nuclei segmentation and labeling for histopathology image data obtained from The Cancer Genome Atlas (TCGA) and check for significance of feature descriptors using K-S test and classification accuracy using support vector machine (SVM) and Random Forests (RF). Our results indicate that we obtain classification accuracy 98.6% and 99.8% in the case of Object-Level features and 82.1% and 86.1% in the case of Spatial Arrangement features, respectively.

Cell nuclei segmentation in glioma histopathology images with color decomposition based active contours

This work discusses the performance of a color decomposition based active contours for segmenting cell nuclei from glioma histopathology. By combining a nuclear staining information obtained from color decomposition with fast variational active contours we obtain unsupervised segmentation of nuclei in histopathological images. Experimental results show promise when compared with different state of the art techniques.