Search

For lower limb disabled driving a car, mechanical manual controllers are mostly used to control the brake and accelerator. However, the joystick is mostly used to drive an airplane; is seldom used in driving a car. This study was aimed at evaluating usability of the joystick-style controller and mechanical manual controller for the lower-limb disabled driving a car. 20 participants were divided into experimental and control groups (10 persons for each group). The experimental group was lower limb disabled and the control group was non-disabled. Each subject performed driving simulator experiment with these two hand controllers, respectively. Driving performance, physiological load and subjective evaluation data were collected during the experiment. Both groups had significantly better driving performance with the joystick-type hand controller than that of the mechanical manual one. They also had significantly lower physiological load (percent of maximal heart rate) with the joystick-type hand controller than that of the mechanical manual one. However, they had similar subjective assessment between these two controllers. This study provides an advanced investigation for applying joystick in driving a car. But, further experiment should be conducted in the real road for confirming safety and efficiency.

$\textbf{Background}$ Named Entity Recognition (NER) is a key task in biomedical text mining. Accurate NER systems require task-specific, manually-annotated datasets, which are expensive to develop and thus limited in size. Since such datasets contain related but different information, an interesting question is whether it might be possible to use them together to improve NER performance. To investigate this, we develop supervised, multi-task, convolutional neural network models and apply them to a large number of varied existing biomedical named entity datasets. Additionally, we investigated the effect of dataset size on performance in both single- and multi-task settings. $\textbf{Results}$ We present a single-task model for NER, a Multi-output multi-task model and a Dependent multi-task model. We apply the three models to 15 biomedical datasets containing multiple named entities including Anatomy, Chemical, Disease, Gene/Protein and Species. Each dataset represent a task. The results from the single-task model and the multi-task models are then compared for evidence of benefits from Multi-task Learning. With the Multi-output multi-task model we observed an average F-score improvement of 0.8% when compared to the single-task model from an average baseline of 78.4%. Although there was a significant drop in performance on one dataset, performance improves significantly for five datasets by up to 6.3%. For the Dependent multi-task model we observed an average improvement of 0.4% when compared to the single-task model. There were no significant drops in performance on any dataset, and performance improves significantly for six datasets by up to 1.1%. The dataset size experiments found that as dataset size decreased, the multi-output model’s performance increased compared to the single-task model’s. Using 50, 25 and 10% of the training data resulted in an average drop of approximately 3.4, 8 and 16.7% respectively for the single-task model but approximately 0.2, 3.0 and 9.8% for the multi-task model. $\textbf{Conclusions}$ Our results show that, on average, the multi-task models produced better NER results than the single-task models trained on a single NER dataset. We also found that Multi-task Learning is beneficial for small datasets. Across the various settings the improvements are significant, demonstrating the benefit of Multi-task Learning for this task., This work was supported by Medical Research Council [grant number MR/M013049/1] and the Cambridge Commonwealth, European and International Trust.

A pocket-size cuffless electronic device for self-measurement of blood pressure (BP) has been developed (Freescan, Maisense Inc., Zhubei, Taiwan). The device estimates BP within 10 s using three embedded electrodes and one force sensor that is applied over the radial pulse to evaluate the pulse wave. Before use, basic anthropometric characteristics are recorded on the device, and individualized initial calibration is required based on a standard BP measurement performed using an upper-arm BP monitor. The device performance in providing valid BP readings was evaluated in 313 normotensive and hypertensive adults in three study phases during which the device sensor was upgraded. A formal validation study of a prototype device against mercury sphygmomanometer was performed according to the American National Standards Institute/Association for the Advancement of Medical Instrumentation/International Organization for Standardization (ANSI/AAMI/ISO) 2013 protocol. The test device succeeded in obtaining a valid BP measurement (three successful readings within up to five attempts) in 55-72% of the participants, which reached 87% with device sensor upgrade. For the validation study, 125 adults were recruited and 85 met the protocol requirements for inclusion. The mean device-observers BP difference was 3.2±6.7 (s.d.) mm Hg for systolic and 2.6±4.6 mm Hg for diastolic BP (criterion 1). The estimated s.d. (inter-subject variability) were 5.83 and 4.17 mm Hg respectively (criterion 2). These data suggest that this prototype cuffless BP monitor provides valid self-measurements in the vast majority of adults, and satisfies the BP measurement accuracy criteria of the ANSI/AAMI/ISO 2013 validation protocol.

Background: Dermatophagoides pteronyssinus (Der p) is one of the most frequently implicated allergens in atopic diseases. Although HLA could play an important role in the development of the IgE response to the Der p allergens, genetic regulation by non- HLA genes influences certain HLA-associated IgE responses to complex allergens. Objective: To clarify genetic control for the expression of Der p–specific IgE responsiveness, we conducted a genome-wide search for genes influencing Der p–specific IgE antibody levels by using 45 Caucasian and 53 African American families ascertained as part of the Collaborative Study on the Genetics of Asthma (CSGA). Methods: Specific IgE antibody levels to the Der p crude allergen and to the purified allergens Der p 1 and Der p 2 were measured. Multipoint, nonparametric linkage analysis of 370 polymorphic markers was performed with the GENEHUNTER program. Results: The best evidence of genes controlling specific IgE response to Der p was obtained in 2 novel regions: chromosomes 2q21-q23 ( P = .0033 for Caucasian subjects) and 8p23-p21 ( P = .0011 for African American subjects). Three regions previously proposed as candidate regions for atopy, total IgE, or asthma also showed evidence for linkage to Der p–specific IgE responsiveness: 6p21 ( P = .0064) and 13q32-q34 ( P = 0.0064) in Caucasian subjects and 5q23-q33 ( P = 0.0071) in African American subjects. Conclusions: No single locus generated overwhelming evidence for linkage in terms of established criteria and guidelines for a genome-wide screening, which supports previous assertions of a heterogeneous etiology for Der p–specific IgE responsiveness. Two novel regions, 2q21-q23 and 8p23-p21, that were identified in this study merit additional study. (J Allergy Clin Immunol 1998;102:436-42.)

PURPOSE: Three-dimensional ultrasound (3DUS) vessel wall volume (VWV) provides a 3D measurement of carotid artery wall remodeling and atherosclerotic plaque and is sensitive to temporal changes of carotid plaque burden. Unfortunately, although 3DUS VWV provides many advantages compared to measurements of arterial wall thickening or plaque alone, it is still not widely used in research or clinical practice because of the inordinate amount of time required to train observers and to generate 3DUS VWV measurements. In this regard, semiautomated methods for segmentation of the carotid media-adventitia boundary (MAB) and the lumen-intima boundary (LIB) would greatly improve the time to train observers and for them to generate 3DUS VWV measurements with high reproducibility. METHODS: The authors describe a 3D algorithm based on a modified sparse field level set method for segmenting the MAB and LIB of the common carotid artery (CCA) from 3DUS images. To the authors' knowledge, the proposed algorithm is the first direct 3D segmentation method, which has been validated for segmenting both the carotid MAB and the LIB from 3DUS images for the purpose of computing VWV. Initialization of the algorithm requires the observer to choose anchor points on each boundary on a set of transverse slices with a user-specified interslice distance (ISD), in which larger ISD requires fewer user interactions than smaller ISD. To address the challenges of the MAB and LIB segmentations from 3DUS images, the authors integrated regional- and boundary-based image statistics, expert initializations, and anatomically motivated boundary separation into the segmentation. The MAB is segmented by incorporating local region-based image information, image gradients, and the anchor points provided by the observer. Moreover, a local smoothness term is utilized to maintain the smooth surface of the MAB. The LIB is segmented by constraining its evolution using the already segmented surface of the MAB, in addition to the global region-based information and the anchor points. The algorithm-generated surfaces were sliced and evaluated with respect to manual segmentations on a slice-by-slice basis using 21 3DUS images. RESULTS: The authors used ISD of 1, 2, 3, 4, and 10 mm for algorithm initialization to generate segmentation results. The algorithm-generated accuracy and intraobserver variability results are comparable to the previous methods, but with fewer user interactions. For example, for the ISD of 3 mm, the algorithm yielded an average Dice coefficient of 94.4% ± 2.2% and 90.6% ± 5.0% for the MAB and LIB and the coefficient of variation of 6.8% for computing the VWV of the CCA, while requiring only 1.72 min (vs 8.3 min for manual segmentation) for a 3DUS image. CONCLUSIONS: The proposed 3D semiautomated segmentation algorithm yielded high-accuracy and high-repeatability, while reducing the expert interaction required for initializing the algorithm than the previous 2D methods.

As the widespread use of high-throughput genomic and protein analysis, more and more experiments have been done to identify the informative genes for various diseases, thus it provides researchers an opportunity to aggregate across multiple microarray experiments via a rank aggregation approach. However, most of current’s microarray rank aggregation methods are either unweighted or prespecified weighted, which has obvious defects. In this paper, We define a new method to weight each ranked list automatically by considering its distances to the other ranked lists and th e agreement with some priori knowledge. Then the problem of integrating ranked lists can be formulated as minimizing an objective criterion which is proved to be NP-hard. Accordingly, we use an Artificial Fish Swarm algorithm (AFSA) to solve the well-defined minimization problem of rank aggregation in terms of decision theory. We conduct two sets of experiments to evaluate the performance of our methods. The experimental results show that the proposed approach owns not only the capability of solving optimization problem but also the biological meaning.