Automated Processing Techniques Research Articles

Radiation diagnosis of pulmonary microcirculation in patients with community-acquired pneumonia

The microcirculatory disfunction plays an important role in the development of pneumonia, determining the clinical course and development of complications. The purpose of the study is the assessment of lung microcirculation disturbance on the different stages of the community-acquired pneumonia and distinguishing it from a post heart attack pneumonia. Materials and methods . 135 patients were radiologically explored. They were admitted to the radiological department with inflammatory signs for the assessment of microcirculation disturbances caused by the pneumonia. We investigated the obtained results. Results . The paper elucidates the stages of community-acquired pneumonia by the results of radiological exploration. In the absence of respiratory diseases, the alterations of lung parenchyma structure were caused by pleural effusion (r=0.71) and pneumonic infiltration zones (posterior parts of the lungs (0.74) and lingular segments (r=0.64)). The microcirculatory disturbances were elicited and counted in automatic mode. The residual alterations were reliably more often observed in the patients with chronic bronchitis. The level of D-dimer was not pathognomic but it was reliably higher in the patients with the PATE (p<0.05). Conclusions . The ambiguous interpretation of disk-shaped atelectasis, avascular sites and areas of pneumonic infiltration of lung tissue with MSCT, requires the SPECT or combined SPECT-CT studies allowing to detect clear triangular microcirculation defects characteristic of pulmonary embolism. The site of inflammatory infiltration effects on the appearance of pulmonary fibrosis. So, the zones of fibrosis can be found in the upper lobes, posterior parts of the lungs and lingular segments reliably more often. The technique for automatic processing of radiological lung exploration allows to get the quantitative assessment the microcirculatory disfunction and the lack of perfusion. It is essential for evaluation of the pathology dynamics and severity and for assessment of the treatment efficiency.

Scalable auto-encoders for gravitational waves detection from time series data

Gravitational waves represent a new opportunity to study and interpret phenomena from the universe. In order to efficiently detect and analyze them, advanced and automatic signal processing and machine learning techniques could help to support standard tools and techniques. Another challenge relates to the large volume of data collected by the detectors on a daily basis, which creates a gap between the amount of data generated and effectively analyzed. In this paper, we propose two approaches involving deep auto-encoder models to analyze time series collected from Gravitational Waves detectors and provide a classification label (noise or real signal). The purpose is to discard noisy time series accurately and identify time series that potentially contain a real phenomenon. Experiments carried out on three datasets show that the proposed approaches implemented using the Apache Spark framework, represent a valuable machine learning tool for astrophysical analysis, offering competitive accuracy and scalability performances with respect to state-of-the-art methods.

A Flexible Autonomous Robotic Observatory Infrastructure for Bentho-Pelagic Monitoring.

This paper presents the technological developments and the policy contexts for the project “Autonomous Robotic Sea-Floor Infrastructure for Bentho-Pelagic Monitoring” (ARIM). The development is based on the national experience with robotic component technologies that are combined and merged into a new product for autonomous and integrated ecological deep-sea monitoring. Traditional monitoring is often vessel-based and thus resource demanding. It is economically unviable to fulfill the current policy for ecosystem monitoring with traditional approaches. Thus, this project developed platforms for bentho-pelagic monitoring using an arrangement of crawler and stationary platforms at the Lofoten-Vesterålen (LoVe) observatory network (Norway). Visual and acoustic imaging along with standard oceanographic sensors have been combined to support advanced and continuous spatial-temporal monitoring near cold water coral mounds. Just as important is the automatic processing techniques under development that have been implemented to allow species (or categories of species) quantification (i.e., tracking and classification). At the same time, real-time outboard processed three-dimensional (3D) laser scanning has been implemented to increase mission autonomy capability, delivering quantifiable information on habitat features (i.e., for seascape approaches). The first version of platform autonomy has already been tested under controlled conditions with a tethered crawler exploring the vicinity of a cabled stationary instrumented garage. Our vision is that elimination of the tether in combination with inductive battery recharge trough fuel cell technology will facilitate self-sustained long-term autonomous operations over large areas, serving not only the needs of science, but also sub-sea industries like subsea oil and gas, and mining.

Laser polishing of 3D printed metallic components: A review on surface integrity

3D Printing is an emerging technology to fabricate complex components in less lead time compared to traditional manufacturing processes. 3D printing enables to build metallic functional components directly from CAD model by depositing the material layer by layer. The fabricated components generally have very rough surfaces and demands for post processing, so that it can directly employ for its end use. Owing to drawbacks like time consuming, skilled labour requirement and limited scope of automation, conventional finishing processes find less application for finishing freeform components. Laser Polishing is a highly productive, contactless and fully automatic post processing technique which is giving promising results to lower the surface roughness of 3D printed metallic components from the past two decades. In laser polishing, when the components are irradiated by the laser radiation, peaks of the surface are melted to a very thin layer and redistributed into the valleys by surface tension and gravity. Laser polishing has shown its ability to polishing varieties of materials from reflective materials like aluminium to high strength materials like Inconel and Titanium alloys. In this present article, a review of laser interaction on surface integrity and mechanical properties of different materials used in metallic 3D printing are reported. The optimum process parameters of laser polishing like laser power, beam diameter, scanning speed and scan spacing/step over are also mentioned with respect to each material.

QCNN Inspired Reconfigurable Keyword Spotting Processor With Hybrid Data-Weight Reuse Methods

The keyword spotting (KWS) system is one of the most important interfaces between humans and machines since it is usually the start of automatic speech recognition and natural language processing techniques. However, for KWS hardware, it is still a problem to make one specified chip both low power and high performed under multiple scenarios, such as in meeting rooms, on different traffic or in parks and so on, for different scenarios own wide range signal-noise-ratios (SNRs). The problem leads to the requirements of balanced design between KWS system accuracy and the hardware cost under various noise types and levels. To overcome the balanced design and tradeoff problems, a complete KWS processor including an Mel-Frequency Cepstrum Coefficients (MFCC) feature extractor and a quantized Convolutional Neural Network (QCNN) accelerator is proposed for wide SNR range and low-power KWS in this paper. Firstly, the approach to quantize CNNs into QCNNs with high accuracy is proposed with considerations of hardware-software tradeoff. With the tradeoff of KWS system accuracy and hardware cost, the 4bit/8bit dual-working-mode strategy is proposed to keep low hardware cost and high accuracy under different scenarios. To be specific, the training, tuning and validating of the CNNs and QCNNs are taken with the dataset of 10 keywords chosen from the Google Command Speech Dataset (GCSD). Secondly, a serial FFT based MFCC extractor is implemented with low power and small footprint. Finally, with a novel hybrid reuse strategy of input data and network weight, a reconfigurable and approximate computing based QCNN accelerator is designed. Implemented and verified under TSMC 22nm ULL technology, with the area of 1.42mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , the QCNN accelerator can achieve 5.26μW/9.08μW power consumption in 4bit/8bit work mode with accuracy of 88% and 93% respectively, which is superior to the state-of-the-art processors.

Establishment and application of an artificial intelligence diagnosis system for pancreatic cancer with a faster region-based convolutional neural network.

Early diagnosis and accurate staging are important to improve the cure rate and prognosis for pancreatic cancer. This study was performed to develop an automatic and accurate imaging processing technique system, allowing this system to read computed tomography (CT) images correctly and make diagnosis of pancreatic cancer faster. The establishment of the artificial intelligence (AI) system for pancreatic cancer diagnosis based on sequential contrast-enhanced CT images were composed of two processes: training and verification. During training process, our study used all 4385 CT images from 238 pancreatic cancer patients in the database as the training data set. Additionally, we used VGG16, which was pre-trained in ImageNet and contained 13 convolutional layers and three fully connected layers, to initialize the feature extraction network. In the verification experiment, we used sequential clinical CT images from 238 pancreatic cancer patients as our experimental data and input these data into the faster region-based convolution network (Faster R-CNN) model that had completed training. Totally, 1699 images from 100 pancreatic cancer patients were included for clinical verification. A total of 338 patients with pancreatic cancer were included in the study. The clinical characteristics (sex, age, tumor location, differentiation grade, and tumor-node-metastasis stage) between the two training and verification groups were insignificant. The mean average precision was 0.7664, indicating a good training effect of the Faster R-CNN. Sequential contrast-enhanced CT images of 100 pancreatic cancer patients were used for clinical verification. The area under the receiver operating characteristic curve calculated according to the trapezoidal rule was 0.9632. It took approximately 0.2 s for the Faster R-CNN AI to automatically process one CT image, which is much faster than the time required for diagnosis by an imaging specialist. Faster R-CNN AI is an effective and objective method with high accuracy for the diagnosis of pancreatic cancer. ChiCTR1800017542; http://www.chictr.org.cn.

Cycling comfort evaluation with instrumented probe bicycle

The cycling comfort level of different cycling infrastructure can strongly influence the comfort perception of cyclists and their route choices. In this paper, the cycling comfort index (CCI) is used to measure the cycling comfort level on cycling infrastructure and describe different cycle track characteristics. An Instrumented Probe Bicycle (IPB), which is equipped with a video camera and a set of sensors including GPS receiver, accelerometer, etc., is employed to collect data while being ridden by cyclist in Singapore. An automatic video processing technique using convolutional neural network (CNN) is applied, such that no direct field measurement is required and the data collection process is less time-consuming. Video-based survey is carried out to capture the correlation between CCI and the comfort perception of cyclists. The extreme gradient boosting (XGBoost) method is employed to build the CCI model dependent on various explanatory variables and survey participants’ ratings. The results show that the overall accuracy of the XGBoost method is 11% higher than the ordered Probit model commonly used in literature.

Automatic Evaluation of Pavement Thickness in GPR Data with Artificial Neural Networks

The ground penetrating radar (GPR) is one of the most frequently recommended non-destructive methods for the pavement thickness measurement. Due to the rapid growth of GPR data in the recent years, the development of automatic data processing techniques is required. In this paper we propose to use one type of artificial neural network, the multilayer perceptron (MLP), for automatic selection of the pavement boundaries. The experimental results indicate that machine learning techniques can be used for robust road structure evaluation.

Daylong acoustic recordings of family and child speech using the HomeBank database

HomeBank (https://homebank.talkbank.org/) is an online database of multi-hour, naturalistic audio recordings of child and family everyday experiences. Corpora in the database include (1) raw audio recordings; (2) corpus metadata including for example social details, standardized test scores, disability reports and status, family data such as number and quantity of siblings, orthographic transcriptions, output of diarization or automatic-speech recognition processing; and (3) tools for analyzing the data (https://github.com/homebankcode/) in a variety of domains. There are currently over a dozen corpora representing over 1100 multi-hour (often daylong) audio recordings. Use of the database is increasing in the scientific community, including researchers of speech, language, computer science, digital signal processing, automatic speech recognition, health sciences, and human development. The utility and extensibility of HomeBank is demonstrated in this talk with several current and ongoing projects that make critical use of the data. We discuss diarization and automatic speech processing techniques, speech and language use in pre-industrial families and groups, early perception and processing in infants, family speech and language dynamics in families of children with disorders, and database management. We are actively soliciting both users and contributors to the database.

Longitudinal development of conversational exchanges in children with hearing loss

Conversations between adults and children have been shown to be an important factor affecting the development of cognition, academic performance, and language use in children. Conversational exchange frequency between parents and children has been shown to increase with age. It has also been demonstrated that degraded sensory input, such as with hearing loss, can result in reduced language, speech, and communication skills in children. This study examines the longitudinal development of conversational exchanges between children with hearing loss and their parents. Thirty-nine families contributed 370 daylong recordings constituting 4337 h of audio collected from a body-worn audio recorder. Automatic speech processing techniques were used to identify and tally conversational exchanges. The main longitudinal effect of age on conversation exchange rate is confirmed, but the effect is weaker and may have a different developmental trajectory for families of children with a hearing loss. This result may be influenced by differences in the development of joint attention between children who are typically developing and those with hearing loss.

Syllable production in hard-of-hearing preschoolers

Expressive language in preschoolers has been shown to be positively related to later language development, although not all studies have shown robust effects. Most studies that consider sex have shown that girls develop expressive language earlier than boys. It has also been widely demonstrated that children with a variety of speech-, language-, and hearing-related disorders show deficits in expressive language skills. Children with hearing loss in particular have shown deficits in consonant production, prosodic control, vowel duration, and mean length of utterance. This study examines the expressive language of preschool children with hearing loss using estimates of syllable production from 366 daylong audio recordings totaling over 4348 h of audio processed with unsupervised automatic speech processing techniques. We found no main effect of sex, but typically-developing children were more voluble on average. Unexpectedly, an interaction effect suggests that typically developing boys may be driving the observed differences. This work adds to the evidence of social and biological variability in the speech production of children, and is further proof-of-concept of developmental speech production work using massive data sets and automatic analysis methods.

Edge Enhancing Accelerated Diffusion Model for Speckle Denoising in Medical Imagery

Speckle noise occurs in a wide range of medical images due to sampling and digital degradation. Removing speckle noise from medical images is the key for further automated processing techniques like segmentation, and can help the clinicians with better diagnosis and therapy. We consider partial differential equation (PDE)-based denoising model which is a modified Euler-Lagrange equation derived from the total variation minimization functional with additional speckle noise constraints. The new PDE model is designed and optimized to rectify speckle noise and enhance edges present in medical imagery. Wealso develop the efficicient and stable discretization techniques for the corresponding speckle denoising model. The method is tested for several types of images including ultrasound images, and it is compared favorably to the conventional denoising model.

회전익항공기 운동모델 개발을 위한 데이터마이닝을 이용한 비행데이터 자동 처리 기법

회전익항공기 운동모델 개발을 위한 데이터마이닝을 이용한 비행데이터 자동 처리 기법

Effectiveness of vacuum consolidation in bonding fibre reinforced polymer (FRP) composites onto concrete surfaces

With the growing popularity of fibre reinforced polymer (FRP) composites in strengthening of structures, new FRP processing methods are required to achieve reliable repairing systems. Application of vacuum resulted in production of components with sound mechanical properties, lower porosity level and accurate fibre management. While the application of automated composite processing techniques is fairly well developed in the aeronautics and marine industry for production of high performance composites, review of the literature reveals that civil infrastructure has still not been benefitted well from the advantages of these methods. This highlights the potential for a comprehensive research program to evaluate efficiency of automated processing techniques in strengthening of infrastructures. This paper will examine interface behaviour of various FRP-concrete connections processed with automated vacuum consolidated techniques as well as wet lay-up and pultrusion. Local and global interfacial characteristics of connections are investigated through series of single lap shear tests and the analytical formulation of governing equations are presented. In addition, the morphology of the composites is examined through scanning electron microscope (SEM). This research reveals the potential of automated FRP processing methods in achieving high level of bond characteristics for structural applications and provides recommendations for future research.

A Novel Approach: Combination of Automated Fiber Placement (AFP) and Additive Layer Manufacturing (ALM)

Automated processing techniques such as automated fiber placement (AFP) or automated tape laying (ATL) are well known nowadays. However, there is still a lot of potential for these methods to achieve better results, especially for large and complex composite structures. In this experimental work, the gap effect with the Automated Fiber Placement is shown and a solution to overcome this drawback is presented. The gaps are particularly apparent on complex and/or double-curved surfaces and reduce the mechanical properties of the composite structure. In order to cover the unavoidable weak area of this effect, a plurality of fiber composite layers are laid on top of one another in order to increase the mechanical properties of components. This in turn makes the components heavier and more expensive to produce. In this new method, the gaps are detected by profile sensor after placement of the tape on the mold. The gaps are filled with the aid of a 3D printer with carbon continuous-fiber reinforced plastics. By combining the 3D printing and AFP technology, composite parts can be manufactured in a more homogeneous manner. Subsequently, the components are produced faster, cheaper and even lighter because of the avoidance of the additional layers.

Precise Measurement of Retinal Vascular Bed Area and Density on Ultra-wide Fluorescein Angiography in Normal Subjects

To characterize and quantify the total retinal vascular bed area (RVBA) and vascular density (VD) in normal eyes using stereographically corrected ultra-wide-field (UWF) fluorescein angiography (FA). Cross-sectional study. Fifty-nine eyes of 31 normal subjects with no evidence of ocular disease underwent FA using the Optos 200Tx (Optos plc, Dunfermline, United Kingdom). Central and peripheral-steered FA images were montaged and stereographically projected. The early-phase FA was used to extract the retinal vasculature as a binary mask. Two independent, masked reading center-certified graders delineated the peripheral edge of the total retinal area (TRA) on a middle-phase frame. The RVBA and TRA were computed automatically in mm2 using software provided by the manufacturer. The VD was calculated by dividing RVBA by TRA. The mean RVBA was 42.3 ± 14.8mm2 for the entire retina, with no difference between male and female subjects (P= .439) or between right and left eyes (P= .407). The mean VD was 4.3% ± 1.4% for the entire retina, with no difference based on sex (P= .629) or laterality (P= .426). A negative correlation was observed between age and both RVBA and VD (RVBA: R=-0.6, P < .001; VD: R=-0.52, P < .001). Pairwise comparisons showed that subjects aged >65 years had smaller RVBA and VD than those younger than 50 years for the entire retina and in all quadrants. RVBA and VD can be extracted from UWF FA images using automated processing techniques and may provide a reliable alternative to measures such as nonperfusion area.

Wavelet-based statistical classification of skin images acquired with reflectance confocal microscopy.

Detecting skin lentigo in reflectance confocal microscopy images is an important and challenging problem. This imaging modality has not yet been widely investigated for this problem and there are a few automatic processing techniques. They are mostly based on machine learning approaches and rely on numerous classical image features that lead to high computational costs given the very large resolution of these images. This paper presents a detection method with very low computational complexity that is able to identify the skin depth at which the lentigo can be detected. The proposed method performs multiresolution decomposition of the image obtained at each skin depth. The distribution of image pixels at a given depth can be approximated accurately by a generalized Gaussian distribution whose parameters depend on the decomposition scale, resulting in a very-low-dimension parameter space. SVM classifiers are then investigated to classify the scale parameter of this distribution allowing real-time detection of lentigo. The method is applied to 45 healthy and lentigo patients from a clinical study, where sensitivity of 81.4% and specificity of 83.3% are achieved. Our results show that lentigo is identifiable at depths between 50μm and 60μm, corresponding to the average location of the the dermoepidermal junction. This result is in agreement with the clinical practices that characterize the lentigo by assessing the disorganization of the dermoepidermal junction.

Analysis of twinning via automated atomistic post-processing methods

twinning is the most prominent and most studied twin mode in hexagonal close-packed materials. Many works have been devoted to describing its nucleation, growth and interactions with other defects. Despite this, gaps and disagreements remain in the literature regarding some fundamental aspects of the twinning process. A rigorous understanding of the twinning process is imperative because without it higher scale models of plasticity cannot accurately capture deformation in important materials such as Mg, Ti, Zr and Zn. Motivated by this necessity, we have studied twinning using molecular dynamics, focusing on automated processing techniques which can extract mechanistic information generalisable to continuum scale deformation. This demonstrates for the first time the automatic identification of twinning dislocation lines and Burgers vectors, and the elasto-plastic decomposition of the deformation gradient inside and around a twin embryo. These results confirm predictions of most authors regarding the dislocation-based twin growth process, while contradicting others who have argued that twin growth stems from a shuffling process with no dislocation line.

MRI correlates of interaction between gender and expressive suppression among the Chinese population

Expressive suppression is a kind of emotion regulation strategies by suppressing behaviors related to emotional responding. Despite the amount of behavioral research on expressive suppression, the structural and functional mechanisms underlying the interaction between gender and expressive suppression in Chinese healthy subjects have remained unknown. In the current study, we assessed the levels of expressive suppression and acquired the structural and functional imaging data from 273 Chinese individuals. A nearly automatic cortical processing technique was used to calculate cortical thickness for each subject. The results from cortical thickness analyses revealed a significant interaction between gender and expressive suppression in the superior frontal gyrus. Then, we conducted the whole-brain functional connectivity analysis with the seed of the superior frontal gyrus to explore the functionally related regions of brain. Subsequent analysis of the interaction between gender and expressive suppression indicated a significant functional connectivity between the superior frontal gyrus and default mode network (DMN) core regions, including the medial prefrontal cortex, precuneus and parahippocampal gyrus. Our results provided the robust empirical evidence illustrating the role of the superior frontal gyrus and DMN in gender difference of expressive suppression among the Chinese population. These findings might have implications for understanding gender difference in emotion processing and regulation.

The mitochondrial landscape of African Americans: An examination of more than 2500 control region haplotypes from 22 U.S. locations

The mitochondrial DNA (mtDNA) control region (16024-576) was Sanger-sequenced for a total of 2563 self-identified African Americans, using automated processing techniques and data review standards exceeding guidelines for forensic applications. Genetic diversity ranged from 0.9952 to 0.9998 in 22 population samples from 20 different states.Haplogroups of African ancestry, found in 82.48% of individuals overall, were most concentrated in the Southeast U.S. and decreased to the north and west. West African and West Central African haplotypes were well-represented in the population samples, especially in the southern U.S. states, while East African haplogroups were observed in low-frequency clusters in a handful of locations across the country. East Asian, Native American, and West Eurasian admixture was present in 3.16%, 2.93%, and 11.43% of samples, respectively. While some geographic substructure was detected across the population samples as clines in admixture frequencies, 20 of the 22 population samples were found to be statistically indistinguishable by pairwise comparisons and AMOVA calculations. Datasets from Hawaii and Idaho, however, were clear outliers. Overall, these more than 2500 control region sequences represent the most comprehensive regional sampling of African American mtDNA diversity to date, and are suitable for use in a forensic mtDNA database. The population data are made available via EMPOP (www.empop.org) and GenBank.