Showing 1–8 of 9 results
Multi-Color Recognition based on Mini-Max Color Threshold for Medical Purpose$15.00
Abstract: This paper discusses the multi-color recognition using the min-max color threshold for
outdoor robot navigation. All colors used in this project are RGB orthogonal color space in order to
see how much of each primary color between min and max that can be observed in the color to be
recognized. The white color value in the color space is set as the object for which the target color to be recognized belongs, while the black color value is set as the object background. The recognition process is done by summing up first the values of the red, green and blue in each color to obtain the rgb sum value, which is then divided by the individual color element to obtain the color threshold. This threshold is compared to the originally color threshold for the recognition, where a satisfactory result is expected as the project is not yet finished.
Keywords: Color recognition, threshold, mini-max, multicolor
Comparing Two Feature Selection Methods for Influenza-A Antivral Resistance Determination$15.00
Abstract: The paper thoroughly analyzes the use of Principal Component Analysis (PCA) in
comparison to Information Gain (IG) as a feature selection method for improving the classification of Influenza-A antiviral resistance. Neural networks were used as the classification method of choice with PCA, while decision trees were the classification of choice with IG. The experiment was conducted on cDNA viral segments of Influenza-A belonging to the H1N1 strain. The 7 Infleunza-A segments generating the best results were used for comparison. Sequences from each segment were further divided into Adamantane-resistant, & non-Adamantane-resistant. Accuracy, sensitivity, specificity precision & time were used as performance measures. Using PCA for feature selection increased preprocessing speeds from an average processing time of 1.5 hours to 5 minutes, as opposed to IG. IG had higher accuracy. The best accuracy generated by PCA & NNs on the M1/M2 was 96.5%, while that of IG & DTs was 98.2% Using PCA features & DTs also generated a comparable accuracy to that of IG features & DT at 97.6% on the M1/M2 segment. There was a 88% increase in feature selection processing speed when using PCA compared to IG on the M1/M2 segment alone.
Keywords: Influenza-A, Principle component analysis (PCA), Machine learning, Information gain,
DNA classification, decision trees, neural networks.
A Study on Automatic Evaluation Method of Pointing and Calling for Nurse Education$15.00
Abstract: Pointing and calling is a method of preventing human error, which is widely used in
Japanese industry. Pointing and calling also has the potential to reduce human error in hospital nursing duties. The development and evaluation of novel technologies are necessary to distinguish if pointing and calling is to be appropriately applied in this context. In this paper, we report on an automatic evaluation method for pointing and calling and present. the evaluation results from an experimental study of the simulated duties of 40 active nurses.
Keywords: Pointing and calling; human error; wearable sensor; evaluation of motion
Experimental Results of 2D Depth-Depth Matching Algorithm Based on Depth Camera Kinect v1$15.00
Abstract: Last year, we proposed a smart transcription algorithm in which a real liver is captured
using a 3D depth camera. As opposed to this, a virtual liver is represented by a polyhedron in STL
(Standard Triangulated Language) format (stereo-lithography) via DICOM (Digital Imaging and
Communication in Medicine) data captured by MRI (magnetic resonance imaging) and/or a CT
(computed tomography) scanner. By comparing the depth image in the real world and the Z-buffer in its virtual world, we quickly identify translation/rotation differences between real and virtual livers in a GPU (graphics processing unit). Then by a randomized steepest descent method based on the differences, we can quickly copy real liver motion to virtual liver motion. In this paper, this
performance (i.e., motion precision and calculation time) of the proposed algorithm is ascertained from several kinds of experiments based on the depth camera Kinect v1. This is the first challenge to use matching real-virtual-depth-images in our algorithm running in 3D AR (augmented reality) with overlapping real and virtual environment.
Keywords: Depth camera image, Z-buffer, steepest descent method, GPU, Parallel processing
Quantification of Interaction between Human Skin Fibroblasts and Collagen by Image Texture Analysis$15.00
Abstract: Collagen plays an important role in maintaining healthy structures in human skin.
Fibroblasts are the cells located in collagen-rich skin dermis and they are responsible for producing
collagen of connective tissue. However, the effects of coating of the culture dish with collagen on
fibroblast culture are still unknown. Therefore, to uncover the effects, we propose a quantitative
method based on Gray-Level Co-occurrence Matrix. This method computes two texture similarity
indices, called “Texture Mean Distance (TMD)” and “Texture Mean Spread (TMS)” by integrating
texture features from images. An experiment with two sets of microscope cell culture images with and without collagen coating demonstrates promising performances of the metrics to identify the effects of collagen on human fibroblasts.
Keywords: cellular images, human skin fibroblasts and collagen, statistical texture features, texture mean distance, texture mean spread
Chaotic Synchronization of Pulse Waves and Respiration$15.00
Abstract: Thus far, attention has been paid to phenomena wherein the cardiovascular system and
respiratory movement system have worked in coordination with one another, which has been studied. On the other hands, the earlier studies have hinted at the importance of considering mental and physical health from a holistic perspective, while taking into consideration the principles that prescribe the chaotic behavior of living organisms. In other words, this raises the issue: The validity of hypothesizing chaos dynamics as a universal principle for living systems that prescribes the chaotic nature of pulse waves and respiration. Therefore, the purpose of this study is to focus on pulse waves and respiration in order to examine the relationship in the chaotic nature between the two. Consequently, the issue presented above was supported. What this implies is that quantitatively assessing synchronous phenomena for the LLE for pulse waves and respiration used in this study is a more highly valid approach for determining people’s mental and physical conditions in the fields of clinical medicine and ergonomics, and therefore it could potentially be applied as a means of substantially supporting the promotion of health.
Keywords: Pulse Waves; Respiration; Chaos; Synchronization
The 3-Dimensional Medical Image Recognition of Right and Left Kidneys by Deep GMDH-type Neural Network$15.00
Abstract: In this study, the deep multi-layered Group Method of Data Handling (GMDH)-type neural
network algorithm using principal component-regression analysis is applied to recognition problems of the right and left kidney regions. The deep multi-layered GMDH-type neural network algorithm can automatically organize the deep neural network architectures which have many hidden layers and these deep neural networks can identify the characteristics of very complex nonlinear systems. The architecture of the deep neural network with many hidden layers is automatically organized using the heuristic self-organization method, so as to minimize the prediction error criterion defined as Akaike’s information criterion (AIC) or Prediction Sum of Squares (PSS). The heuristic self-organization method is a type of the evolutionary computation. In this deep GMDH-type neural network, principal component-regression analysis is used as the learning algorithm of the weights in the deep GMDHtype neural network, and multi-colinearity does not occur and stable and accurate prediction values are obtained. This new algorithm is applied to the medical image recognitions of the right and left kidney regions. The optimum neural network architectures, which fit the complexity of the right and left kidney regions, are automatically organized and the right and left kidney regions are automatically recognized and extracted by the organized deep GMDH-type neural networks. The recognition results are compared with the conventional sigmoid function neural network trained using the back propagation method and it is shown that this deep GMDH-type neural networks are useful for the medical image recognition problems of the right and left kidney regions.
Keywords: Deep neural network, GMDH, medical image recognition, evolutionary computation,
Impacts of Radio Frequency Interference on Human Brain Waves and Neuropsychological Changes$15.00
Abstract: This study investigates the neuro-psychological impacts of radio frequency interference
(RFI) by correlating the brain waves under RFI exposure. In our experiments, twelve participants were tested under controlled RF exposure at 1.8 GHz in an anechoic chamber under one-blind condition. The electroencephalograph (EEG) were recorded for each 5-minute time trial before, during and after RF exposure with an intensity of 10% of the ICNIRP Guideline exposure limits. The psychological responses of the participants are inquired with psychometric scales before and after the experiment to analyze the correlationship between RFI and the emotional reaction of humans. Statistical tests indicate that theta and alpha waves were able to be characterized, and the significant differences were observed in both alpha waves and theta waves between the data before and after exposure from the consequence of paired t-tests. This initial study indicated that short term exposure to RFI may cause impacts on brain waves, but may not lead to any direct emotional changes by the participants.
Keywords: EEG, Radio frequency interference, RF exposure, Brain waves, Neuro-psychological