Integration Of Multiple Features Research Articles

Degradable Multilayer Fabric Sensor with Wide Detection Range and High Linearity.

Integration of multiple superior features into a single flexible pressure sensor would result in devices with greater versatility and utility. To apply the device to a variety of scenarios and solve the problem of accumulation of e-waste in the environment, it is highly desirable to combine degradability and wide-range linearity characteristics in a single device. Herein, we reported a degradable multilayer fabric (DMF) consisting of an ellipsoidal carbon nanotube (ECNT) and polyvinylpyrrolidone/cellulose acetate electrospun fibers (PEF). The alternative layer-by-layer stacking of the ECNT and PEF notably accelerates the sensitivity toward pressure. The optimized device demonstrated a sensitivity of 3.38 kPa-1 over a wide measurement range from 0.1 to 500 kPa, as well as great mechanical stability over 2000 cycles. A good degradation performance was confirmed by both Fourier transform infrared (FTIR) characterization and decomposition experiments in sodium hydroxide solution. The fabricated sensor is capable of precepting a variety of physiological scenarios including subtle arterial pulse, dancing training, walking postures, and accidental falls. This work throws light onto the fundamental understanding of the mechanical interfacial coupling in piezoresistive materials and provides possibilities for the design and development of on-demand wearable electronics.

From CAD model to WAM component: implementation of complex geometries using the example of a hydrogen tank.

Abstract Hydrogen is expected to play a decisive role on the way to climate neutral transportation. This paper explores the innovative use of wire arc Directed Energy Deposition (waDED) in the manufacturing of a double walled, vacuum insulated liquid hydrogen storage tank. The study demonstrates the feasibility of the waDED process for the manufacturing of tank shells and furthermore the integration of heat exchanger channels into tank shells. Key findings include the development of a suitable process chain with integration of multiple features to ease manufacturing. However, challenges such as thermal shrinkage of the shells as well as geometrical deviations of the outer tank heat exchanger are encountered. Future research will focus on improvements in the process reliability with regards to geometric accuracy as well as in-depth testing under liquid hydrogen condition.

Automated breast imaging report generation based on the integration of multiple image features in a metadata format for shared decision-making

Automated breast imaging report generation based on the integration of multiple image features in a metadata format for shared decision-making

Replay Attack Detection Using Integrated Glottal Excitation Based Group Delay Function and Cepstral Features

The automatic speaker verification system is susceptible to replay attacks. Recent literature has focused on score-level integration of multiple features, phase information-based features, high frequency-based features, and glottal excitation for the detection of replay attacks. This work presents glottal excitation-based all-pole group delay function (GAPGDF) features for replay attack detection. The essence of a group delay function based on the all-pole model is to exploit information from the speech signal phase spectrum in an effective manner. Further, the performance of integrated high-frequency-based CQCC features with cepstral features, subband spectral centroid-based features (SCFC and SCMC), APGDF, and LPC-based features is evaluated on the ASVspoof 2017 version 2.0 database. On the development set, an EER of 3.08% is achieved, and on the evaluation set, an EER of 9.86% is achieved. The proposed GAPGDF features provide an EER of 10.5% on the evaluation set. Finally, integrated GAPGDF and GCQCC features provide an EER of 8.80% on the evaluation set. The computation time required for the ASV systems based on various integrated features is compared to ensure symmetry between the integrated features and the classifier.

Diversified Teaching of English Translation Courses in Colleges and Universities Based on the Integration of Multiple Features

Abstract The development of informatization in education has provided the possibility of using resource libraries to enhance English translation courses. Facing this new demand, this paper adopts an entity-based approach to connect multimodal entities with other structured entities, to construct a multimodal knowledge graph for English translation courses in colleges and universities. On this basis, the recommendation model of collaborative filtering is introduced to provide students with personalized English translation exercise recommendation services according to the mastery of knowledge points processed by the knowledge graph. After the model is designed, the knowledge points of the English translation course in a university are firstly extracted physically, and then two classes are selected in the university for controlled experiments. The number of successes in terms of vertical depth strategy is 264, the success rate is 88%, and the success rate of recommendation based on the centrality of knowledge points and contribution value is 94.66%. The mean score of the experimental class was 72.12 and the control class was 67.48. The significant difference in the scores can be confirmed by the fact that the p-value of the independent square root test for the two classes was less than 0.5. English teachers can benefit from this model’s assistance in evaluating English translation resources and providing a variety of teaching methods.

Visualizaciones de datos accesibles con Highcharts JS

Data literacy is a key element of information literacy. In a context where more and more sectors are making use of data visualization, it is essential to incorporate accessibility into the design of these resources to ensure access to information for all citizens. The aim of this paper is to introduce the Highcharts library for creating data visualizations. The installation process, the creation of a simple chart, and the integration of multiple accessibility features are shown.

Infants' visual perception without feature-binding.

We reveal a unique visual perception before feature-integration of colour and motion in infants. Visual perception is established by the integration of multiple features, such as colour and motion direction. The mechanism of feature integration benefits from the ongoing interplay between feedforward and feedback loops, yet our comprehension of this causal connection remains incomplete. Researchers have explored the role of recurrent processing in feature integration by studying a visual illusion called 'misbinding', wherein visual characteristics are erroneously merged, resulting in a perception distinct from the originally presented stimuli. Anatomical investigations have revealed that the neural pathways responsible for recurrent connections are underdeveloped in early infants. Therefore, there is a possibility that younger infants could potentially perceive the physically presented visual information that adults miss due to misbinding. Here, we demonstrate that infants less than half a year old showed no misbinding; thus, they perceived the physically presented visual information, while infants more than half a year old perceived incorrectly integrated visual information, showing misbinding. Our findings indicate that recurrent processing barely functions in infants younger than six months of age and that visual information that should have been originally integrated is perceived as it is without being integrated.

Automated Echocardiographic Detection of Heart Failure With Preserved Ejection Fraction Using Artificial Intelligence

BackgroundDetection of heart failure with preserved ejection fraction (HFpEF) involves integration of multiple imaging and clinical features which are often discordant or indeterminate. ObjectivesThe authors applied artificial intelligence (AI) to analyze a single apical 4-chamber transthoracic echocardiogram video clip to detect HFpEF. MethodsA 3-dimensional convolutional neural network was developed and trained on apical 4-chamber video clips to classify patients with HFpEF (diagnosis of heart failure, ejection fraction ≥50%, and echocardiographic evidence of increased filling pressure; cases) vs without HFpEF (ejection fraction ≥50%, no diagnosis of heart failure, normal filling pressure; controls). Model outputs were classified as HFpEF, no HFpEF, or nondiagnostic (high uncertainty). Performance was assessed in an independent multisite data set and compared to previously validated clinical scores. ResultsTraining and validation included 2,971 cases and 3,785 controls (validation holdout, 16.8% patients), and demonstrated excellent discrimination (area under receiver-operating characteristic curve: 0.97 [95% CI: 0.96-0.97] and 0.95 [95% CI: 0.93-0.96] in training and validation, respectively). In independent testing (646 cases, 638 controls), 94 (7.3%) were nondiagnostic; sensitivity (87.8%; 95% CI: 84.5%-90.9%) and specificity (81.9%; 95% CI: 78.2%-85.6%) were maintained in clinically relevant subgroups, with high repeatability and reproducibility. Of 701 and 776 indeterminate outputs from the Heart Failure Association-Pretest Assessment, Echocardiographic and Natriuretic Peptide Score, Functional Testing (HFA-PEFF), and Final Etiology and Heavy, Hypertensive, Atrial Fibrillation, Pulmonary Hypertension, Elder, and Filling Pressure (H2FPEF) scores, the AI HFpEF model correctly reclassified 73.5% and 73.6%, respectively. During follow-up (median: 2.3 [IQR: 0.5-5.6] years), 444 (34.6%) patients died; mortality was higher in patients classified as HFpEF by AI (HR: 1.9 [95% CI: 1.5-2.4]). ConclusionsAn AI HFpEF model based on a single, routinely acquired echocardiographic video demonstrated excellent discrimination of patients with vs without HFpEF, more often than clinical scores, and identified patients with higher mortality.

A Fullerene Seeded Strategy for Facile Construction of Nitrogen‐Doped Carbon Nano‐Onions as Robust Electrocatalysts

AbstractCarbon nano‐onions (CNOs) as a novel form of carbon materials hold peculiar structural features but their electrocatalytic applications are largely discouraged by the demanding synthesis conditions (e.g., ≥1500 °C and vacuum). Using C60 fullerene molecules as the sacrificial seeds and melamine as the main feedstock, herein, a novel strategy for the facile construction of CNOs nanoparticles is presented with ultrafine sizes (≈5 nm) at relatively low temperatures (≤900 °C) and atmospheric pressure. During the calcination, in‐depth characterizations reveal that C60 can retain the melamine‐derived graphitic carbon nitride from complete sublimation at high temperatures (≥700 °C). Owing to the N removal and subsequent pentagon generation, severely deformed graphitic fragments together with the disintegrated C60 molecules merge into larger sized nanosheets with high curvature, eventually leading to the formation of N‐doped defect‐rich CNOs. Owing to the integration of multiple favorable structural features of pentagons, edges, and N dopants, the CNOs obtained at 900 °C present superior oxygen reduction half‐wave potential (0.853 VRHE) and zinc–air cathode performance to the commercial Pt/C (0.838 VRHE). Density functional theory calculation further uncovers that the carbon atoms adjacent to the N‐doped edged pentagons are turned into the ORR‐active sites with O2 protonation as the rate‐determining step.

The effect of transcutaneous auricular vagus nerve stimulation (taVNS) on cognitive control in multitasking

Current research in brain stimulation suggests transcutaneous auricular vagus nerve stimulation (taVNS) as a promising tool to modulate cognitive functions in healthy populations, such as attention, memory, and executive functions. Empirical evidence in single-task contexts, suggests that taVNS promotes holistic task processing, which strengthens the integration of multiple stimulus features in task processing. However, it is unclear how taVNS might affect performance in multitasking, where the integration of multiple stimuli leads to an overlap in stimulus response translation processes, increasing the risk of between-task interference (crosstalk). In a single-blinded, sham-controlled, within-subject design, participants underwent taVNS while performing a dual task. To assess the effects of taVNS, behavioral (reaction times), physiological (heart rate variability, salivary alpha-amylase), and subjective psychological variables (e.g., arousal) were recorded over three cognitive test blocks. Our results revealed no overall significant effect of taVNS on physiological and subjective psychological variables. However, the results showed a significant increase in between-task interference under taVNS in the first test block, but not in the subsequent test blocks. Our findings therefore suggest that taVNS increased integrative processing of both tasks early during active stimulation.

A joint multi-modal learning method for early-stage knee osteoarthritis disease classification

Osteoarthritis (OA) is a progressive and chronic disease. Identifying the early stages of OA disease is important for the treatment and care of patients. However, most state-of-the-art methods only use single-modal data to predict disease status, so that these methods usually ignore complementary information in multi-modal data. In this study, we develop an integrated multi-modal learning method (MMLM) that uses an interpretable strategy to select and fuse clinical, imaging, and demographic features to classify the grade of early-stage knee OA disease. MMLM applies XGboost and ResNet50 to extract two heterogeneous features from the clinical data and imaging data, respectively. And then we integrate these extracted features with demographic data. To avoid the negative effects of redundant features in a direct integration of multiple features, we propose a L1-norm-based optimization method (MMLM) to regularize the inter-correlations among the multiple features. MMLM was assessed using the Osteoarthritis Initiative (OAI) data set with machine learning classifiers. Extensive experiments demonstrate that MMLM improves the performance of the classifiers. Furthermore, a visual analysis of the important features in the multimodal data verified the relations among the modalities when classifying the grade of knee OA disease.

BEAR-H: An Intelligent Bilateral Exoskeletal Assistive Robot for Smart Rehabilitation

One typical application of a robotic exoskeleton is to automate rehabilitation, where the robot is worn by a stroke patient and provides assistance to help perform repetitive motions and regain motor functions. The deployment of exoskeletons can alleviate the shortage of experienced therapists and would also play a vital role in countries with aging populations. However, the intelligence level of existing exoskeletons is relatively low, wherein a robot cannot adapt to either the online change of a subject’s motion (e.g., the gait pattern) or the variation of his/her body parameters (i.e., a new subject who is going to wear the robot), potentially resulting in conflict between human and robot and possibly even leading to physical damage. As such, the application of a robotic exoskeleton in clinical studies is limited. This article introduces a new bilateral exoskeletal assistive robot for rehabilitation (BEAR-H) in which the main novelty is the integration of multiple intelligent features, such as gait recognition and synchronization, cloud-computing diagnosis, and individualized gait generation. Such an integration helps the robot to better understand the patient’s condition and hence provide effective assistance, by the end achieving smart rehabilitation. BEAR-H is a successfully commercialized product, and its performance has been validated in actual clinical studies with 30 patients, producing experimental results from different aspects that are analyzed and presented.

Regulation of gene expression during ontogeny of physiological function in the brackishwater amphipod Gammarus chevreuxi.

Embryonic development is a complex process involving the co-ordinated onset and integration of multiple morphological features and physiological functions. While the molecular basis of morphological development in embryos is relatively well known for traditional model species, the molecular underpinning of the development of physiological functions is not. Here, we used global gene expression profiling to investigate the transcriptional changes associated with the development of morphological and physiological function in the amphipod crustacean Gammarus chevreuxi. We compared the transcriptomes at three timepoints during the latter half of development, characterised by different stages of the development of heart form and function: 10days post fertilisation (dpf, Early: no heart structure visible), 15 dpf (Middle: heart present but not fully functional), and 18 dpf (Late: regular heartbeat). Gene expression profiles differed markedly between developmental stages, likely representing a change in the activity of different processes throughout the latter period of G. chevreuxi embryonic development. Differentially expressed genes belonged to one of three distinct clusters based on their expression patterns across development. One of these clusters, which included key genes relating to cardiac contractile machinery and calcium handling, displayed a pattern of sequential up-regulation throughout the developmental period studied. Further analyses of these transcripts could reveal genes that may influence the onset of a regular heartbeat. We also identified morphological and physiological processes that may occur alongside heart development, such as development of digestive caeca and the cuticle. Elucidating the mechanisms underpinning morphological and physiological development of non-model organisms will support improved understanding of conserved mechanisms, addressing the current phylogenetic gap between relatively well known model species.

Identification of Prognostic Markers in Argentinian Acute Lymphoblastic Leukemia Pediatric Patients Through Transcriptome Analysis: Differential Gene Expression, Mutational Status and Immune Microenvironment

PURPOSE Acute lymphoblastic leukemia (ALL) is the most incident pediatric cancer. Although considerable progress has been made on treatment efficacy and survival rates, 15%-30% of patients relapse and/or die. We aimed to identify molecular profiles and microenvironment makeup in leukemic bone marrow samples that could help to better predict disease outcome. METHODS We performed RNA-seq on bone marrow samples from pediatric ALL patients at diagnosis (n = 37). Patients were recruited under a multi-center clinical protocol in Argentina (median follow-up: 31 months). We analyzed differential gene expression, gene set variations, mutations in candidate genes, and fusion genes among clinico-pathological features. The abundance of immune-cell populations was inferred by digital cytometry (MIXTURE) and a “cytolytic score” based on the expression of five genes specific to cytotoxic cells. RESULTS We detected: (1) 37 differentially expressed genes (DEG) between poor vs good responders to prednisone; (2) 71 DEG between high vs standard-risk groups; (3) 13 DEG between patients who died/relapsed vs those who did not; and (4) 35 DEG between patients that developed severe therapy-related acute toxicity vs those who did not (|log2FC|> 1; P.adj < .05). We observed that 15%-30% of the DEG corresponded to lncRNAs. We found six differentially expressed pathways relevant to cancer and leukocyte biology among risk groups ( P < .01). We identified 17 mutations and three fusion genes in 44% of patients; the presence of these mutations shortened the relapse-free survival (Cox- P-val = .006). High cytolytic score was associated with activated CD8+T cells, immune cell trafficking, and bone marrow niche signaling genesets, suggesting potential candidates for immunotherapies. Higher CD8+T-cell/NK at diagnosis was marginally associated with worse event-free survival (hazard-ratio = 5.39; Cox- P-val = .08). CONCLUSION Transcriptomic sequencing allowed the analysis and integration of multiple molecular features that might improve pediatric ALL outcome prediction.

On integration of multiple features for human activity recognition in video sequences

On integration of multiple features for human activity recognition in video sequences

MitoCarta3.0: an updated mitochondrial proteome now with sub-organelle localization and pathway annotations.

The mammalian mitochondrial proteome is under dual genomic control, with 99% of proteins encoded by the nuclear genome and 13 originating from the mitochondrial DNA (mtDNA). We previously developed MitoCarta, a catalogue of over 1000 genes encoding the mammalian mitochondrial proteome. This catalogue was compiled using a Bayesian integration of multiple sequence features and experimental datasets, notably protein mass spectrometry of mitochondria isolated from fourteen murine tissues. Here, we introduce MitoCarta3.0. Beginning with the MitoCarta2.0 inventory, we performed manual review to remove 100 genes and introduce 78 additional genes, arriving at an updated inventory of 1136 human genes. We now include manually curated annotations of sub-mitochondrial localization (matrix, inner membrane, intermembrane space, outer membrane) as well as assignment to 149 hierarchical ‘MitoPathways’ spanning seven broad functional categories relevant to mitochondria. MitoCarta3.0, including sub-mitochondrial localization and MitoPathway annotations, is freely available at http://www.broadinstitute.org/mitocarta and should serve as a continued community resource for mitochondrial biology and medicine.

Adaptive Multi-Feature Reliability Re-Determinative Correlation Filter for Visual Tracking

Model drift is a challenging issue for visual object tracking. Most available approaches aim to address this issue by constructing of a stronger discriminative prediction model with the integration of multiple features. In this article, we also address the issue of model drift using multiple features, but we consider the fusion problem from a different point of view, namely, strengthening the features that are suitable for the current scenario while weakening the remaining ones. Therefore, an advanced tracker that adaptively redetermines the reliability for each feature during the tracking process is proposed. Furthermore, to correctly evaluate and redetermine these reliabilities, two different solutions, called model evaluation and numerical optimization, are proposed, and two independent trackers corresponding to these two solutions are implemented. Extensive experiments have been designed on five large datasets to validate the following: 1) The proposed tracking framework is superior for making the tracking model more robust, and 2) the two solutions proposed for redetermining the reliability for each feature are effective. As expected, the two implemented trackers do indeed improve the accuracy and robustness compared to state-of-the-art trackers. Especially on VOT2016, the proposed trackers based on model evaluation and numerical optimization achieve outstanding EAO scores (i.e., <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.453</b> and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.428</b> , respectively), outperforming the recently developed top trackers by a large margin.

Design and in vitro evaluation of electrospun shape memory polyurethanes for self-fitting tissue engineering grafts and drug delivery systems.

Integration of multiple features including shape memory, biodegradation, and sustained drug delivery in a single material offers the opportunity to significantly improve the abilities of implantable devices for cardiovascular system regeneration. Two types of shape memory polyurethanes (SMPUs): PU-PLGA and PU-PLLA/PEG differing in soft segments composition that comprising blends of various biodegradable polyols, i.e. D,l-lactide-co-glycolide diol (o-PLGA), poly(e-caprolactone) diols (o-PCL) with various molecular weights, poly-l-lactide diol (o-PLLA), polyethylene glycol (o-PEG) were synthesized and further utilized to electrospun nanofibrous - rapamycin (Rap) delivery system. Structure characterization by Fourier transform infrared spectroscopy (FTIR), differential scanning calorimetry (DCS) and hydrophilicity measurements were performed to gain more insights on the influence of the particular units of the softs segments on the transition temperature (Ttrans), shape recovery, degradation profile, and drug release kinetics. In vitro study in PBS solution revealed that incorporation of o-PLGA segments to SMPUs is favorable over o-PEG as increased shape memory performance was observed. Moreover, presence of PLGA in PU-PLGA gave more predictable degradation profile in comparison to PU-PLLA/PEG system. Human Cardiac Fibroblasts (HCF) viability tests in vitro confirmed that the amount of Rap released from evaluated PU-PLLA/PEG/Rap and PU-PLGA/Rap drug delivery systems was sufficient to inhibit cells growth on the surface of the tested materials.

Next-generation interfaces for studying neural function.

Monitoring and modulating the diversity of signals used by neurons and glia in a closed-loop fashion is necessary to establish causative links between biochemical processes within the nervous system and observed behaviors. As developments in neural-interface hardware strive to keep pace with rapid progress in genetically encoded and synthetic reporters and modulators of neural activity, the integration of multiple functional features becomes a key requirement and a pressing challenge in the field of neural engineering. Electrical, optical and chemical approaches have been used to manipulate and record neuronal activity in vivo, with a recent focus on technologies that both integrate multiple modes of interaction with neurons into a single device and enable bidirectional communication with neural circuits with enhanced spatiotemporal precision. These technologies not only are facilitating a greater understanding of the brain, spinal cord and peripheral circuits in the context of health and disease, but also are informing the development of future closed-loop therapies for neurological, neuro-immune and neuroendocrine conditions.

Novel drug-independent sedation level estimation based on machine learning of quantitative frontal electroencephalogram features in healthy volunteers

BackgroundSedation indicators based on a single quantitative EEG (QEEG) feature have been criticised for their limited performance. We hypothesised that integration of multiple QEEG features into a single sedation-level estimator using a machine learning algorithm could reliably predict levels of sedation, independent of the sedative drug used. MethodsIn total, 102 subjects receiving propofol (N=36; 16 male/20 female), sevoflurane (N=36; 16 male/20 female), or dexmedetomidine (N=30; 15 male/15 female) were included in this study of healthy volunteers. Sedation level was assessed using the Modified Observer's Assessment of Alertness/Sedation (MOAA/S) score. We used 44 QEEG features estimated from the EEG data in a logistic regression algorithm, and an elastic-net regularisation method was used for feature selection. The area under the receiver operator characteristic curve (AUC) was used to assess the performance of the logistic regression model. ResultsThe performances obtained when the system was trained and tested as drug-dependent mode to distinguish between awake and sedated states (mean AUC [standard deviation]) were propofol=0.97 (0.03), sevoflurane=0.74 (0.25), and dexmedetomidine=0.77 (0.10). The drug-independent system resulted in mean AUC=0.83 (0.17) to discriminate between the awake and sedated states. ConclusionsThe incorporation of large numbers of QEEG features and machine learning algorithms is feasible for next-generation monitors of sedation level. Different QEEG features were selected for propofol, sevoflurane, and dexmedetomidine groups, but the sedation-level estimator maintained a high performance for predicting MOAA/S independent of the drug used. Clinical trial registrationNCT 02043938; NCT 03143972.