discrimination capacity
Recently Published Documents


TOTAL DOCUMENTS

46
(FIVE YEARS 14)

H-INDEX

13
(FIVE YEARS 1)

2022 ◽  
Vol 14 (2) ◽  
pp. 320
Author(s):  
Jinyu Bao ◽  
Xiaoling Zhang ◽  
Tianwen Zhang ◽  
Xiaowo Xu

Most existing SAR moving target shadow detectors not only tend to generate missed detections because of their limited feature extraction capacity among complex scenes, but also tend to bring about numerous perishing false alarms due to their poor foreground–background discrimination capacity. Therefore, to solve these problems, this paper proposes a novel deep learning network called “ShadowDeNet” for better shadow detection of moving ground targets on video synthetic aperture radar (SAR) images. It utilizes five major tools to guarantee its superior detection performance, i.e., (1) histogram equalization shadow enhancement (HESE) for enhancing shadow saliency to facilitate feature extraction, (2) transformer self-attention mechanism (TSAM) for focusing on regions of interests to suppress clutter interferences, (3) shape deformation adaptive learning (SDAL) for learning moving target deformed shadows to conquer motion speed variations, (4) semantic-guided anchor-adaptive learning (SGAAL) for generating optimized anchors to match shadow location and shape, and (5) online hard-example mining (OHEM) for selecting typical difficult negative samples to improve background discrimination capacity. We conduct extensive ablation studies to confirm the effectiveness of the above each contribution. We perform experiments on the public Sandia National Laboratories (SNL) video SAR data. Experimental results reveal the state-of-the-art performance of ShadowDeNet, with a 66.01% best f1 accuracy, in contrast to the other five competitive methods. Specifically, ShadowDeNet is superior to the experimental baseline Faster R-CNN by a 9.00% f1 accuracy, and superior to the existing first-best model by a 4.96% f1 accuracy. Furthermore, ShadowDeNet merely sacrifices a slight detection speed in an acceptable range.


Nanophotonics ◽  
2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Alfredo Franco ◽  
Verónica Vidal ◽  
Marcos Gómez ◽  
Olga Gutiérrez ◽  
María Martino ◽  
...  

Abstract Developing a simple, fast, and label-free method for discrimination between live cancer cells and normal cells in biological samples still remains a challenge. Here, a system is described that fulfills these features to analyze individual living cells. The system consists of a gold nanohole array biosensor plus a microscope optical design to isolate the spectral response of a single cell. It is demonstrated that differences in the spectral behavior between tumor (colorectal cancer cell lines and primary cells from colorectal cancer tissue) and non-tumor cells (peripheral blood mononuclear cells, skin fibroblasts and colon epithelial cells) are influenced by the actin cortex, which lies within the short penetration depth of the surface plasmon electromagnetic field. The efficacy of this system was assessed by the analysis of about one thousand single cells showing the highest discrimination capacity between normal colon epithelial cells and colorectal cancer cells from surgical specimens, with values of sensitivity and specificity ranging 80–100% and 87–100%, respectively. It is also demonstrated that cell discrimination capacity of the system is highly reduced by disrupting the formation of actin cortex. This plasmonic system may find wide applications in biomedicine and to study key cellular processes that involve the actin cortex, including proliferation, differentiation, and migration.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Carlos Fernando Valencia ◽  
Oscar David Lucero ◽  
Onofre Casas Castro ◽  
Andrey Alexandrovich Sanko ◽  
Peter Alfonso Olejua

AbstractThe pandemic of SARSCov2 infection has created a challenge in health services worldwide. Some scales have been applied to evaluate the risk of intubation, such as the ROX and HACOR. The objective of this study is to compare the predictive capacity of the HACOR scale and the ROX index and define the optimal cut-off points. Study of diagnostic tests based on a retrospective cohort. Composite outcome was the proportion of patients that needed endotracheal intubation (ETI) or died of COVID19 pneumonia. Discrimination capacity was compared by the area under the curve of each of the two scales and the optimal cut-off point was determined using the Liu method. 245 patients were included, of which 140 (57%) required ETI and 152 (62%) had the composite end result of high-flow nasal cannula (HFNC) failure. The discrimination capacity was similar for the two scales with an area under receiver operating characteristic curve of 0.71 and 0.72 for the HACOR scale for the ROX index, respectively. The optimal cut-off point for the ROX index was 5.6 (sensitivity 62% specificity 65%), while the optimal cut-off point for the HACOR scale was 5.5 (sensitivity 66% specificity 65%). The HACOR scale and the ROX index have a moderate predictive capacity to predict failures to the HFNC strategy. They can be used in conjunction with other clinical variables to define which patients may require invasive mechanical ventilation.


2021 ◽  
Author(s):  
Shahid Nazir ◽  
Atif Adnan ◽  
Rahat Rehman ◽  
Muhammad Jawad ◽  
Reem Almheiri ◽  
...  

Abstract Y-chromosome short tandem repeat polymorphisms (Y-STRs) are important in many areas of human genetics. Y chromosomal STRs being normally utilized in the field of forensic exhibit low haplotype diversity in endogamous populations and fail to discriminate among male relatives from same pedigree. Rapidly mutating Y-STRs (RM Y-STRs) have been paid much attention in last decade. These 13 RM Y STRs have high mutation rates (>10-2) and have considerably higher haplotype diversity and discrimination capacity than conventionally used Y-STRs showing remarkable power, when it comes to differentiation in paternal lineages in endogamous populations. Previously, we have analyzed 2–4 generation, 99 pedigrees covering 1568 pairs of men covering 1–6 meioses from all over Pakistan and 216 male relatives from 18 deep rooted endogamous Sindhi pedigrees covering 1-7 meioses. Here we are presenting 861 pairs of men from 63 endogamous pedigrees covering 1-6 meioses from Punjabi population of Punjab, Pakistan. Mutations were frequently observed at DYF399 and DYF403 while no mutation was observed at DYS526a/b. The rate of differentiation ranged from 29.70% (first meiosis) to 80.95% (fifth meiosis) while overall (1 to 6 meiosis) differentiation was 59.46%. Combining previously published data with newly generated data, an overall differentiation rate was 38.79% based on 5176 pairs of men related by 1–20 meioses, while Y-filer differentiation was 9.24% based on 3864 pairs. Using father-son pair data from the present and previous studies, we also provide updated RM Y-STR mutation rates.


Sensor Review ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Rabeb Faleh ◽  
Sami Gomri ◽  
Khalifa Aguir ◽  
Abdennaceur Kachouri

Purpose The purpose of this paper is to deal with the classification improvement of pollutant using WO3 gases sensors. To evaluate the discrimination capacity, some experiments were achieved using three gases: ozone, ethanol, acetone and a mixture of ozone and ethanol via four WO3 sensors. Design/methodology/approach To improve the classification accuracy and enhance selectivity, some combined features that were configured through the principal component analysis were used. First, evaluate the discrimination capacity; some experiments were performed using three gases: ozone, ethanol, acetone and a mixture of ozone and ethanol, via four WO3 sensors. To this end, three features that are derivate, integral and the time corresponding to the peak derivate have been extracted from each transient sensor response according to four WO3 gas sensors used. Then these extracted parameters were used in a combined array. Findings The results show that the proposed feature extraction method could extract robust information. The Extreme Learning Machine (ELM) was used to identify the studied gases. In addition, ELM was compared with the Support Vector Machine (SVM). The experimental results prove the superiority of the combined features method in our E-nose application, as this method achieves the highest classification rate of 90% using the ELM and 93.03% using the SVM based on Radial Basis Kernel Function SVM-RBF. Originality/value Combined features have been configured from transient response to improve the classification accuracy. The achieved results show that the proposed feature extraction method could extract robust information. The ELM and SVM were used to identify the studied gases.


2021 ◽  
Vol 11 (8) ◽  
pp. 1039
Author(s):  
Elad Omer ◽  
Yoram Braw

Performance validity tests (PVTs) are used for the detection of noncredible performance in neuropsychological assessments. The aim of the study was to assess the efficacy (i.e., discrimination capacity) of a novel PVT, the Multi-Level Pattern Memory Test (MPMT). It includes stages that allow profile analysis (i.e., detecting noncredible performance based on an analysis of participants’ performance across stages) and minimizes the likelihood that it would be perceived as a PVT by examinees. In addition, it utilizes nonverbal stimuli and is therefore more likely to be cross-culturally valid. In Experiment 1, participants that were instructed to simulate cognitive impairment performed less accurately than honest controls in the MPMT (n = 67). Importantly, the MPMT has shown an adequate discrimination capacity, though somewhat lower than an established PVT (i.e., Test of Memory Malingering—TOMM). Experiment 2 (n = 77) validated the findings of the first experiment while also indicating a dissociation between the simulators’ objective performance and their perceived cognitive load while performing the MPMT. The MPMT and the profile analysis based on its outcome measures show initial promise in detecting noncredible performance. It may, therefore, increase the range of available PVTs at the disposal of clinicians, though further validation in clinical settings is mandated. The fact that it is an open-source software will hopefully also encourage the development of research programs aimed at clarifying the cognitive processes involved in noncredible performance and the impact of PVT characteristics on clinical utility.


2021 ◽  
Author(s):  
Oscar Lucero ◽  
Carlos Fernando Valencia ◽  
Onofre Casas Castro ◽  
Andrey Sanko ◽  
Peter Alfonso Olejua

Abstract BackgroundThe pandemic of SARSCov2 infection has created a challenge in health services worldwide. Some scales have been applied to evaluate the risk of intubation, such as the ROX and HACOR. The objective of this study is to compare the predictive capacity of the HACOR scale and the ROX index and define the optimal cut-off points.MethodsStudy of diagnostic tests based on a retrospective cohort. Composite outcome was the proportion of patients that needed orotracheal intubation or died of COVID19 pneumonia. Discrimination capacity was compared by the area under the curve of each of the two scales and the optimal cut-off point was determined using the Liu method.Results245 patients were included, of which 140 (57.14%) required OTI and 152 (62.04%) had the composite end result of HFNC failure. The discrimination capacity was similar for the two scales with an AUROC of 0.71 and 0.72 for the HACOR scale for the ROX index, respectively. The optimal cut-off point for the ROX index was 5.62 (sensitivity 62% specificity 65%), while the optimal cut-off point for the HACOR scale was 5.5 (sensitivity 66% specificity 65%).ConclusionsThe HACOR scale and the ROX index have a moderate predictive capacity to predict failures to the HFNC strategy. They can be used in conjunction with other clinical variables to define which patients may require invasive mechanical ventilation.


Author(s):  
Goutam Gadiraju ◽  
Daniel Andrade

This study investigated the differences in amplitude discrimination capacity between two stimuli delivered to adjacent fingertips on the same hand (contralateral delivery) and stimuli delivered to two fingers on opposite hands (bilateral delivery).  The measures were obtained in order to study the impact of lateral inhibition via interhemispheric connections on cortical centers on opposite sides of the somatosensory cortex in comparison to lateral inhibition occurring between adjacent cortical centers within the same hemisphere. Using the Cortical Metrics Brain Gauge™ device, amplitude discrimination capacity of 37 healthy subjects was assessed at several different durations, ranging from 40 to 500 msec, of vibrotactile stimulation delivered contralaterally and bilaterally. The results demonstrate a significant difference in amplitude discrimination capacity between the two conditions for stimulus duration of 200ms, with performance being better for the contralateral delivery of the stimuli than the bilateral condition for most tested durations. Task performance was roughly the same for the two conditions at the extremes of short (40ms) and long (500ms) stimulus durations. Amplitude discrimination capacity improved with longer stimulus durations in both bilateral and contralateral conditions. Though slight variation was observed at the level of each individual subject, overall, it is clear that local lateral inhibition plays a role in assessing the two stimuli delivered to the same hand that gives same-handed discrimination an advantage over two-handed discrimination. Additionally, the trends identified may be useful in guiding future experimentation that investigates clinical assessments of deficits in cortical processing that is mediated by callosal connections.


2020 ◽  
Vol 295 (6) ◽  
pp. 1315-1324
Author(s):  
Noora R. Al-Snan ◽  
Safia A. Messaoudi ◽  
Yahya M. Khubrani ◽  
Jon H. Wetton ◽  
Mark A. Jobling ◽  
...  

Abstract We have determined the distribution of Y-chromosomal haplotypes and predicted haplogroups in the ethnically diverse Kingdom of Bahrain, a small archipelago in the Arabian Gulf. Paternal population structure within Bahrain was investigated using the 27 Y-STRs (short tandem repeats) in the Yfiler Plus kit to generate haplotypes from 562 unrelated Bahraini males, sub-divided into four geographical regions—Northern, Capital, Southern and Muharraq. Yfiler Plus provided a significant improvement over the 17-locus Yfiler kit in discrimination capacity (from 77% to 87.5% overall), but discrimination capacity differed widely between regions from 98.4% in Muharraq to 75.2% in the Northern region, an unusually low value possibly resulting from recent rapid population expansion. Clusters of closely related male lineages were seen, with only 79.4% of donors displaying unique haplotypes and 59% of instances of shared haplotypes occurring within, rather than between, regions. Haplogroup prediction indicated diverse origins of the population with a predominance of haplogroups J2 and J1, both typical of the Arabian Peninsula, but also haplogroups such as B2 and E1b1a likely originating in Africa, and H, L and R2 likely indicative of migration from South Asia. Haplogroup frequencies differed significantly between regions, with J2 significantly more common in the Northern region compared with the Southern, possibly due to differential settlement by Baharna and Arabs. Our study shows that paternal lineage population structure can exist even over small geographical scales, and that highly discriminating genetic tools are required where rapid expansions have occurred within tightly bounded populations.


Sign in / Sign up

Export Citation Format

Share Document