Search

In this study, a VR bike system designed to play on Google Street View was proposed. The VR Bike System combines a VR System connected to a Game-Bike on which a player can ride and a VR helmet which the player wears to facilitate immersion in the VR environment. The VR environment contains a series of VR360 pictures of street views from Google maps. The series of VR360 pictures construct a series of VR spaces which connect to form a tunnel. When the player rides the Game-Bike, the camera of the VR system starts to move along the tunnel. By wearing the VR helmet, the player can easily look around the VR envi- ronment. The player can ride the Game-Bike to control the speed of the VR system camera moving along the tunnel. In our system, it is easy to travel all over the world by riding Game-Bike in the VR environment.

In dentistry, all ceramic restorations were widely used because of perfect esthetic, especially the zirconia ceramic. Now in digital dentistry, zirconia dental restorations are mostly made from digital manufacturing system such as the computer-aided design and computer-aided manufacturing (CAD/CAM) or three-dimension printing (3DP). After producing, the sintering process is indispensable due to the increase in the mechanical properties. Notably, the side effect of shrinkage of the sintering process is difficult to predict or control and cannot be studied deeply. Reflecting the accurate of zirconia restoration is lower, especially the most important factor of restoration fitness. So the poor fitness of restoration easily leads to secondary caries or micro leakage that the tooth will decay again and the remaining teeth will need to be removed completely. In this paper, the 3DP is the target manufacturing process to avoid the high cost of CAD/CAM processing; the 3DP product needs to be of high precision after the sintering process. However, the shrinkage of the 3DP product is difficult to predict and cannot be studied deeply. Therefore, different shrinkage rates of experimental pieces following the manufacturer’s instructions of the sintering process are first predicted in CAE analysis, experimental design, and regression analysis. The results are then applied in the manufacture of incisor restoration to verify the shrinkage. This can make the restoration fit in the patient’s mouth properly and reduce the medical operation time. It helps the 3DP to successfully apply the dentures.

The study proposed an application to detect cryptomeria trees which had been damaged by squirrels from an aerial image. Each pixel of the aerial image is classified into damaged tree pixels or healthy pixels by super vector machine (SVM) developed in this paper. The application achieves about 82.24% true positive rate (TPR) in detecting damaged trees and about 1.30% false positive rate (FPR). It is a smart tool for monitoring smart forests.

BACKGROUND/PURPOSE: Virtual reality has the advantage to provide rich sensory feedbacks for training balance function. This study tested if the home-based virtual reality balance training is more effective than the conventional home balance training in improving balance, walking, and quality of life in patients with Parkinson's disease (PD). METHODS: Twenty-three patients with idiopathic PD were recruited and underwent twelve 50-minute training sessions during the 6-week training period. The experimental group (n = 11) was trained with a custom-made virtual reality balance training system, and the control group (n = 12) was trained by a licensed physical therapist. Outcomes were measured at Week 0 (pretest), Week 6 (posttest), and Week 8 (follow-up). The primary outcome was the Berg Balance Scale. The secondary outcomes included the Dynamic Gait Index, timed Up-and-Go test, Parkinson's Disease Questionnaire, and the motor score of the Unified Parkinson's Disease Rating Scale. RESULTS: The experimental and control groups were comparable at pretest. After training, both groups performed better in the Berg Balance Scale, Dynamic Gait Index, timed Up-and-Go test, and Parkinson's Disease Questionnaire at posttest and follow-up than at pretest. However, no significant differences were found between these two groups at posttest and follow-up. CONCLUSION: This study did not find any difference between the effects of the home-based virtual reality balance training and conventional home balance training. The two training options were equally effective in improving balance, walking, and quality of life among community-dwelling patients with PD. Language: en

In this study, we investigate the factors influencing the playability of a music rhythm game, and then design a game with a higher level of playability. Three categories were used to investigate playability. They were functionality, structural, and audiovisual. Four popular games are used to carry out the comparison of playability. They include ‘Don't Tap The White Tile V2’, ‘Deemo’, ‘Cytus’, and ‘LiveLove’. The results of user satisfaction of the four compared games suggest ‘Cytus’ has a higher playability than the other three games in all three of the categories. In the comparison of ‘Cytus’ with the game "Anima" designed by the current writers, ‘Anima’ achieves better results than ‘Cytus’. In the satisfaction with function category, ‘Anima’ and ‘Cytus’ achieve 3.83 and 3.80, respectively, indicating little significant difference in results. For the structural category, It was found that players immerse themselves in "Anima" better than ‘Cytus’, the satisfactions were 3.93 and 3.65, respectively. For the audiovisual category, it was found that the cooperation of audio and video and the design of characters in ‘Anima’ were better than ‘Cytus’, the satisfactions were 4.44 and 3.90, respectively. This study, provides new rules for the design of music rhythm games with a higher playability and demonstrates how following these rules to develop a new game ‘Anima’ was able to obtain successful results.

Reading Tang dynasty poetry may improve both character education and language proficiency of children in nursery school. However, Tang poetry is a little abstract and difficult to understand for preschool children. To overcome this difficulty, in our study, a digital Game based Tang Poetry learning system (GTPLS) is developed. An investigation was conducted of 5 to 6 years old children separated into two groups. One group, designated as the T-group, used a traditional learning model and the other, designated as G-group, used the GTPLS model. The traditional learning model of the T-group mainly used the recitation of Tang Poetry from books. The results of this study showed that at the first test conducted for both groups the T-group and the G-group achieved 15% and 65% respectively. At the second test 10% and 90%, The third and forth test results were 25%–100% and 75%–100%. The results show that at least four attempts at the test were required for the T-group to pass the test. However, it only required three attempts for all of the G-group to pass the test and they maintained the same result even for the fourth time of testing.

In Taiwan, breast cancer has become the second leading type of cancerous diseases among women. The incidence and mortality rates keep rising, and mammography remains to be the only effective screening technique which is capable of detecting breast cancer at an early stage. High mammographic density is a strong risk factor for breast cancer. Based on BI-RADS categories, mammograms are classified into four categories (D1-D4) based on the percentage of dense area (PDA). However, reporting of breast density suffers from high inter and intra observer variability. Because the risk of breast cancer is at least three times greater in women with density (D3&D4) than in women with density D1, this paper proposes a local entropy method to identify the higher density (D3&D4) from (D1&D2) by two features. There are 406 mammograms with four categories collected for the test. The higher density (D3&D4) can be identified from lower density (D1&D2) in the correction of 100%. The Az of receiver operating characteristic curve of 0.9996 can be achieved.

This paper introduces a multi-level morphological active contour (MMAC) algorithm to identify and delineate tree crowns in mountainous forest based on rasterized airborne lidar data. MMAC is a generalized tree crown mapping algorithm which can accommodate multiple heads in a crown as well as overlapping crowns. The MMAC algorithm comprises three steps: bottom up erosion (BUE) which identifies stand candidates, top down dilation (TDD) which estimates the crown periphery, and an active contour model (ACM) which delineates crown contours. Three sample plots were selected in Alishan National Scenic Area, Taiwan, (predominantly alder, sugi, and red cypress) for evaluation of the algorithm. When compared with ground survey data, the algorithm achieved an average detection accuracy of 24 percent omission error and 13 percent commission error in identifying individual trees in mountainous forest stands. Detection accuracy is potentially related to stand density.

Spectral signature coding (SSC) is generally performed by encoding spectral values of a signature across its spectral coverage followed by the Hamming distance to measure signature similarity. The effectiveness of such an SSC largely relies on how well the Hamming distance can capture spectral variations that characterize a signature. Unfortunately, in most cases, this Hamming-distance-based SSC does not provide sufficient discriminatory information for signature analysis because the Hamming distance does not take into account the band-to-band variation, in which case the Hamming distance can be considered as a memoryless distance. This paper extends the Hamming-distance-based SSC to an approach, referred to as spectral feature probabilistic coding (SFPC), which introduces a new concept into SSC that uses a criterion with memory to measure spectral similarity. It implements the well-known arithmetic coding (AC) in two ways to encode a signature in a probabilistic manner, called circular SFPC and split SFPC. The values resulting from the AC is then used to measure the distance between two spectral signatures. In order to demonstrate advantages of using AC-based SSC in signature analysis, a comparative analysis is also conducted against spectral binary coding.

A recent paper by Chang develops a new algorithm, called the simplex growing algorithm, which has shown promise in end member extraction. There is an erroneous description made for one of synthetic image experiments. While making a simple correction would have sufficed, a series of studies has led to interesting and intriguing results on how to determine an appropriate number of end members p, how to design a better end member extraction algorithm, and how to use an effective technique to perform dimensionality reduction.

Ineffective triggering (IT) is the most common manifestation of patient-ventilator asynchrony in mechanically ventilated patients. IT in the expiratory phase (ITE) accounts for the majority of IT and is associated with characteristic features of flow and airway pressure deflection, caused by ineffective effort from the patient. The purpose of this study was to quantify the characteristics of flow and airway pressure deflections of ITE and, using a computerized algorithm, to evaluate their usefulness in the detection of ITEs.Prospective, clinical study.Medical intensive care unit in a 1,000-bed university hospital.A total of 14 mechanically ventilated adult patients with patient-ventilator asynchrony.None.We analyzed 5,899 breaths and found that 1,831 were ITEs. The average values for maximum flow deflection (F(def)) and maximum airway pressure deflection (P(def)) in ITEs were 13.94 +/- 8.0 L/min and 1.91 +/- 0.97 cm H2O. With a starting value of 0.1 L/min for F(def) and 0.01 cm H2O for P(def), the area under the receiver operating characteristics curve of F(def) and P(def) for the detection of ITEs was 0.98 and 0.97, respectively. Sensitivity and specificity for the detection of ITEs were 91.5% and 96.2% for F(def), respectively, for a cutoff value of 5.45 L/min, and 93.3% and 92.9% for Pdef, for a cutoff value of 0.45 cm H2O.We conclude that accurately detecting and quantifying ITEs is feasible using a computerized algorithm based on F(def) and P(def). Such a computerized estimation of patient-ventilator interaction might be helpful for adjusting ventilator settings in an intensive care unit.

A new shape recognition-based neural network built with universal feature planes, called Shape Cognitron (S-Cognitron) is introduced to classify clustered microcalcifications. The architecture of S-Cognitron consists of two modules and an extra layer, called 3D figure layer lies in between. The first module contains a shape orientation layer, built with 20 cell planes of low level universal shape features to convert first-order shape orientations into numeric values, and a complex layer, to extract second-order shape features. The 3D figure layer is a feature extract-display layer that extracts the shape curvatures of an input pattern and displays them as a 3D figure. It is then followed by a second module made up of a feature formation layer and a probabilistic neural network-based classification layer. The system is evaluated by using Nijmegen mammogram database and experimental results show that sensitivity and specificity can reach 86.1 and 74.1%, respectively.

Physiological signal monitoring is a key function in the application of home health care. In recent years, various devices for physiological signal monitoring in different environment were developed for assisting health care. However, monitoring alone can’t fit the needs of many scenarios. As such, it is often that the patient requires some daily healthcare related interaction. It is also essential that a system not only monitors but also serves as an assistance to the patient, such as medicine taking reminder, home visiting arrangement, etc. for supporting the patient with interaction capabilities in daily care scenarios. Based on this consideration, this paper has presented a home health care box which provides health monitor and fits a variety of scenarios to achieve health management. In order for the home health box to be able to adapt for different scenarios, a message embedding mechanism is also presented in this paper.

In this paper, we propose a new region-of-interest (ROI) coding method called fractal based JPEG2000 ROI coding for the further improvement of JPEG2000 used in mammograms. This method provides the advantage that it is not necessary for user to provide any ROI information before coding.

A Neocognitron-like neural network built with universal feature planes, called shape cognitron (S-cognitron) is introduced to classify clustered microcalcifications (MCCs). The S-cognitron is composed of two modules. The first module consists of (a) a shape orientation layer, to convert first-order shape orientations into numeric values, and (b) a complex layer to extract second-order shape features. Following is a 3-D figure layer to extract the shape curvatures. It is then followed by a second module made up of a feature formation layer and a probabilistic neural network (PNN)-based classification layer, to construct "potential" high-order shape features and perform the classification. Experimental results show the promise of the system.

A system for automatically detecting microcalcifications in digital mammograms is presented. The proposed system, based on a sequence of preprocessing steps (gradient enhancement, mean contrast enhancement and Gaussian blurring-deblurring process) followed by segmentation using entropy thresholding, can effectively and efficiently detect the suspicious microcalcifications. The performance of the designed system is evaluated by skilled radiologists and shows encouraging results.

This paper presents a prototype of a computer-aided design (CAD) diagnostic system for mammography screening to automatically detect and classify microcalcifications (MCCs) in mammograms. It comprises four modules. The first module, called the Mammogram Preprocessing Module, inputs and digitizes mammograms into 8-bit images of size 2048x2048, extracts the breast region from the background, enhances the extracted breast and stores the processed mammograms in a data base. Since only clustered MCCs are of interest in providing a sign of breast cancer, the second module, called the MCCs Finder Module, finds and locates suspicious areas of clustered MCCs, called regions of interest (ROIs). The third module, called the MCCs Detection Module, is a real time computer automated MCCs detection system that takes as inputs the ROIs provided by the MCCs Finder Module. It uses two different window sizes to automatically extract the microcalcifications from the ROIs. It begins with a large window of size 64x64 to quickly screen mammograms to find large calcified areas, this is followed by a smaller window of size 8x8 to extract tiny, isolated microcalcifications. Finally, the fourth module, called the MCCs Classification Module, classifies the detected clustered microcalcifications into five categories according to BI-RADS (Breast Imaging Reporting and Data System) format recommended by the American College of Radiology. One advantage of the designed system is that each module is a separate component that can be individually upgraded to improve the whole system. Despite that it is still is a prototype system a preliminary clinical evaluation at TaiChung Veterans General Hospital (TCVGH) has shown that the system is very flexible and can be integrated with the existing Picture Archiving and Communications System (PACS) currently implemented in the Department of Radiology at TCVGH.

Subpixel detection in multispectral imagery presents a chal- lenging problem due to relatively low spatial and spectral resolution. We present a generalized constrained energy minimization (GCEM) ap- proach to detecting targets in multispectral imagery at subpixel level. GCEM is a hybrid technique that combines a constrained energy mini- mization (CEM) method developed for hyperspectral image classification with a dimensionality expansion (DE) approach resulting from a gener- alized orthogonal subspace projection (GOSP) developed for multispec- tral image classification. DE enables us to generate additional bands from original multispectral images nonlinearly so that CEM can be used for subpixel detection to extract targets embedded in multispectral im- ages. CEM has been successfully applied to hyperspectral target detec- tion and image classification. Its applicability to multispectral imagery is yet to be investigated. A potential limitation of CEM on multispectral imagery is the effectiveness of interference elimination due to the lack of sufficient dimensionality. DE is introduced to mitigate this problem by expanding the original data dimensionality. Experiments show that the proposed GCEM detects targets more effectively than GOSP and CEM without dimensionality expansion. © 2000 Society of Photo-Optical Instrumenta- tion Engineers. (S0091-3286(00)01205-8)

The detection of venous beading in retinal images provides an early sign of diabetic retinopathy and plays an important role as a preprocessing step in diagnosing ocular diseases. We present a computer-aided diagnostic system to automatically detect venous bead- ing of blood vessels. It comprises of two modules, referred to as the blood vessel extraction module (BVEM) and the venus beading detection module (VBDM). The former uses a bell-shaped Gaussian kernel with 12 azimuths to extract blood vessels while the latter applies a neural network-based shape cognitron to detect venous beading among the extracted blood vessels for diagnosis. Both modules are fully computer- automated. To evaluate the proposed system, 61 retinal images (32 beaded and 29 normal images) are used for performance evaluation. © 2000 Society of Photo-Optical Instrumentation Engineers. (S0091-3286(00)01305-2) Subject terms: bell-shaped Gaussian matched filter; blood vessel extraction mod- ule; detection; extraction; neural network; retinal images; shape cognitron; venus beading detection module.

MR images have been used extensively in clinical trials in recent years because they are harmless to the human body and can obtain detailed information by scanning the same slice with various frequencies and parameters. In this paper, we want to detect the breast tissues within multi-spectral MR images. In the image classification, we apply a support vector machine (SVM) to breast multi-spectral magnetic resonance images to classify the tissues of the breast. In order to verify the feasibility and efficiency of this method, evaluations using classification rate and likelihood ratios are adopted based on manifold assessment and a series of experiments are conducted and compared with the commonly used C-means (CM) for performance evaluation. The results show that the SVM method is a promising and effective spectral technique for MR image classification.