Search

Most ultrasonic backscatter method excites a short single-pulse and then analyses the bone's response for diagnosing osteoporosis. However, the bone responses to the ultrasound excitation have not been fully understood, such as the response to amplitude modulation (AM) excitation, which may contain more information about bone characteristics for diagnosing. The objectives of this study were to observe the response that the cancellous bones to the AM excitation, and then to investigate extracting AM backscatter parameter for estimating bone mineral density (BMD) and structure. An innovative instrument was developed and realized both AM excitation and real-time calculation parameter AIB AM . The results showed that AIB AM has strong and stable correlations with BMD and structure model index (SMI) ( $\vert \mathrm{R}\vert =0.82-0.91, \mathrm{p} ). These results indicate that AM ultrasonic backscatter method combined with the portable device might have the potential for screening and diagnosing osteoporosis.

Objective: the purpose of this paper was to investigate the effect of spectral computation methods on the estimation of the four ultrasonic backscatter parameters, namely, the apparent integrated backscatter (AIB), the zero frequency intercept of apparent backscatter (FIAB), the frequency slope of apparent backscatter (FSAB), and the backscatter spectral centroid shift (SCS) from the backscattered signal of interest (SOI), and their subsequent correlations with cancellous bone parameter [bone volume/total volume (BV/TV)]. Methods: ultrasonic backscatter measurements were performed on 26 bovine cancellous bone specimens using a 1.0-MHz focused transducer. Four spectral estimation algorithms, including the classical periodogram, the autoregressive (AR) Burg algorithm, the AR covariance algorithm, and the AR modified covariance algorithm, were used to calculate the ultrasonic parameters. Influence of the signal's delay time (T1) and its length (T2) on the strength of correlation between BV/TV and backscatter parameters was also studied. Results: the results have demonstrated that the AR-based estimators provide much more reliable and stronger correlations between the BV/TV and backscatter parameters than the classical periodogram. Recommendations for choosing SOI were also suggested. Conclusion: these results indicate that the AR-based method has a promising potential to enhance the performance of evaluation and diagnosis of the cancellous bone using the ultrasonic backscatter method. Significance: the enhancement of the correlation may provide a positive impact on the ultrasonic backscatter method to diagnose and monitor the bone quantity.

Osteoporosis is a systemic skeletal disease, which is characterized by the deterioration of microstructures and the decrease of bone mineral density (BMD). Ultrasonic backscatter technique has a promising potential to evaluate microstructures and BMD of cancellous bone for the diagnosis of osteoporosis. The dynamic time warping (DTW)algorithm, measuring the similarity between two signals, has been widely used in speech and image recognition. The purpose of this study is to investigate the feasibility of the DTW algorithm in extracting features from ultrasonic backscatter signals and estimating the microstructure of cancellous bones. Ultrasonic backscatter measurements were performed on twenty-six bovine cancellous bone specimens using an ultrasonic backscatter bone diagnostic system with a focused broadband transducer, which has a center frequency of 1.04 MHz. The dynamic time warped distance (DTWD)feature was extracted from the cost matrix between the ultrasonic backscatter signals and the reference signal. The associations between ultrasonic backscatter features (including DTWD)and trabecular microstructures (i.e., the average trabecular number (Tb. N)and the average trabecular bone spacing (Tb. Sp)), and BMD were analyzed using the simple Pearson's correlations and Partial correlations. The results showed that the DTWD significantly correlated with the Tb.N (R = −0.86±0.09, p

Deep, convolutional neural networks have become the state-of-the-art method for automatic Facial Expression Recognition (FER). Because of the small size and controlled conditions of most FER datasets, however, models can still overfit to the training dataset and struggle to generalize well to new data. We present a novel approach of using crowdsourced label distributions for improving the generalization performance of convolutional neural networks for FER. We implement this as a loss layer regularizer, where the ground truth labels are combined with crowdsourced labels in order to construct a noisy output distribution during training. We use a label disturbance method in which training examples are randomly replaced with incorrect labels drawn from the combined label probability distribution. We compare the performance of our disturbed and undisturbed models in cross-validation testing on the extended Cohn-Kanade dataset and cross-dataset experiments on the MMI, JAFFE, and FER2013 datasets. We find that using our proposed method, test performance is improved on both the MMI and JAFFE datasets. Our results suggest that using nonuniform probability distributions to disturb training can improve generalization performance of CNNs on other FER datasets.

This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a re-formulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other deep models, e.g., Faster R-CNN, for improving high-level tasks on hazy images. Experimental results on both synthesized and natural hazy image datasets demonstrate our superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Furthermore, when concatenating AOD-Net with Faster R-CNN, we witness a large improvement of the object detection performance on hazy images.

A model illustrating the gas-liquid two-phase flows (GLTFs) of slug raw-milk in micro tubes was built, and an infrared-curtain-based sensor was designed for non-contact recognition of raw milk in GLTFs. An infrared curtain signal acquisition site was set at both upstream and downstream for analysis of time domain, frequency spectrum and cross-correlation. Photos of two-phase flows were taken by a high-speed camera and used as a synchronous control of signal analysis. The analysis of infrared curtain signals shows that the spectral energy of raw-milk GLTFs at low-speed condition is concentrated at the low-frequency section, but at high-speed condition it shifts to the high-frequency section with two peaks nearby. Therefore, the infrared-curtain-based non-contact sensor succeeded in recognition of raw milk GLTFs in micro tubes. Compared with a contact-typed pressure sensor, this non-contact sensor can extremely reduce the interference on flow patterns. This sensor severs as a theoretical basis for further research on pattern recognition and flowing mechanism of GLTFs. This study also provides some clues for exploration of infrared-curtain-based non-contact computation of raw-milk flow quantity.

Based on the wireless sensor network technology, the paper designs an on-line monitoring system for farmland soil information. The system consists of two parts, namely, the wireless sensor network and the remote data managing center. Between them, the former mainly includes the micro controller chip STC89C52 and the wireless transceiver module APC220, and the latter running on the host computer is developed by Lab view. Moreover, the soil humidity can be on-line monitored successfully by the fuzzy algorithm in this system. The experimental results show that 6 sensors can construct network correctly in the interval distance of 200 meters, and the soil moisture can be controlled within the error range of 1.5%. The performance of the proposed system is tested, and it indicates that the system is reliable and effective.