A Soft-YoloV4 for High-Performance Head Detection and Counting

Blockage of pedestrians will cause inaccurate people counting, and people’s heads are easily blocked by each other in crowded occasions. To reduce missed detections as much as possible and improve the capability of the detection model, this paper proposes a new people counting method, named Soft-YoloV4, by attenuating the score of adjacent detection frames to prevent the occurrence of missed detection. The proposed Soft-YoloV4 improves the accuracy of people counting and reduces the incorrect elimination of the detection frames when heads are blocked by each other. Compared with the state-of-the-art YoloV4, the AP value of the proposed head detection method is increased from 88.52 to 90.54%. The Soft-YoloV4 model has much higher robustness and a lower missed detection rate for head detection, and therefore it dramatically improves the accuracy of people counting.

Study of Coagulopathies in Covid 19 Positive Patients & Their Correlation with Outcome of Disease

INTRODUCTION COVID-19 started in November 2019 as an infection with a new strain of Corona virus and spread across all geographic regions. It has been observed that various coagulation abnormalities are not infrequent in COVID-19. Bleeding and coagulation abnormalities have surfaced as one of the mechanisms that could be related to increased mortality associated with it. Through our work, we look forward to discovering more on this association & we believe our study could provide new insight that could save additional lives. AIMS & OBJECTIVES - To study coagulation abnormalities in Covid-19 Positive patients. - To correlate these coagulation abnormalities with severity of disease and outcome of Covid-19 Positive patients. Material & Methods:This is a prospective study being carried out on the Intensive Care Unit (ICU) admitted Covid 19 positive patients, in a tertiary care hospital. Fifty cases have been studied so far, to look for coagulation abnormalities. Covid 19 positive patients by RNA detection by RT PCR method, admitted in ICU of hospital have been investigated for Prothrombin Time (PT), Activated Partial Thromboplastin Time (APTT), Thrombin Time (TT), Fibrinogen levels and D-Dimer levels.The results of these investigations were correlated with clinical condition of these ICU patients, to assess the prognosisand outcome, of Covid-19 Positive patients. Results: Fifty COVID positive patients admitted in ICU have been studied & out of these 19 patients eventually expired (Non-survivors group) and 31 recovered from their illness (Survivors group). These fifty patients were investigated,at the time of presentation in ICU. Prothrombin time (PT)was prolonged in Covid 19 positive patients. Prothrombin time (PT) values in theSurvivors group ranged from 13.47 to 15.36 seconds(Mean 14.42 seconds). Prothrombin time (PT) values in theNon-survivors group ranged from 13.63 to 15.43 seconds (Mean 14.53 seconds).Normal control of Prothrombin time (PT) was 13 seconds. Prothrombin time (PT) values in the Survivors group were compared with Non-survivors group with ap value = 0.865(statistically not significant). Activated partial thromboplastin time (APTT)values in theSurvivors group ranged from 33.44 to 36.38 seconds(Mean 34.91 seconds). Activated partial thromboplastin time (APTT) values in theNon-survivors group ranged from 33.68 to 38.32 seconds(Mean 36.00 seconds). Normal control of activated partial thromboplastin time (APTT) was 34 seconds. Activated partial thromboplastin time (APTT) values in the Survivors group were compared with Non-survivors group with ap value = 0.397(statistically not significant). Thrombin time (TT)values in theSurvivors group ranged from 17.61 to 19.81 seconds(Mean 18.71 seconds). Thrombin time (TT) values in theNon-survivors group ranged from 18.68 to 22.32 seconds(Mean 20.50 seconds). Normal control of thrombin time (TT) was 18 seconds. Thrombin time (TT) values in the Survivors group were compared with Non-survivors group with ap value = 0.072(statistically not significant). Fibrinogen levelsin theSurvivors group ranged from 378 mgm/dl to 441mgm/dl(Mean 410mgm/dl). Fibrinogen levels in theNon-survivors group ranged from 331 mgm/dl to 419mgm/dl(Mean 375mgm/dl). Normal values for fibrinogen levels were 150 to 450 mgm/dl. Fibrinogen levels in the Survivors group were compared with Non-survivors group with ap value = 0.184(statistically not significant). D-Dimer levelswere increased in Covid 19 positive patients. D-Dimer levels in theSurvivors group ranged from 854 ngm/ml to 1847ngm/ml(Mean 1401ngm/ml). D-Dimer levels in theNon-survivors group ranged from 1308 ngm/ml to 2858 ngm/ml(Mean 2083ngm/ml). Normal values for D-Dimer levels were 135 to 250 ngm/ml. D-Dimer levels in the Survivors group were compared with Non-survivors group with ap value = 0.130(statistically not significant). Conclusion Ours is a small single centre study, however, shows coagulopathies in Covid 19 positive patients. Although, there is a difference between coagulation abnormalities in survivor & non-survivor group of ICU patients but this difference is statistically not significant. Disclosures No relevant conflicts of interest to declare.

Enhancing aphid detection framework based on ORB and convolutional neural networks

Methods to detect directly aphids based on convolutional neural networks (CNNs) are unsatisfactory because aphids are small and usually are specially distributed. To enhance aphid detection efficiency, a framework based on oriented FAST and rotated BRIEF (ORB) and CNNs (EADF) is proposed by us to detect aphids in images. Firstly, the key point is to find regions of aphids. Points generated by the ORB algorithm are processed by us to generate suspected aphid areas. Regions are fed into convolutional networks to train the model. Finally, images are detected in blocks with the trained model. In addition, in order to solve the situation that the coordinates are not uniform after the image is segmented, we use a coordinate mapping method to unify the coordinates. We compare current mainstream target detection methods. Experiments indicate that our method has higher accuracy than state-of-the-art two-stage methods that the AP value of RetinaNet with EADF is 0.385 higher than RetinaNet without it and the Cascade-RCNN with EADF is more than without it by 43.3% on value of AP, which demonstrates its competency.

The Characteristic of Auditory Function and Cochlear Synaptopathy in a Noise-exposed Cohort: A Cross-sectional Study

ObjectivesTo determine whether noise-induced cochlear synaptopathy occurs in humans.DesignYoung workers with occupational noise-exposure from a shipyard were recruited for participation in the current study. Age-matched workers in the same shipyard who had no noise-exposure were enrolled in the control group. The speech-in-noise scores, gap detection thresholds and SP/AP values were tested and compared between the two groups. The correlations of both the speech-in-noise scores and the gap detection threshold with the SP/AP value were calculated and analyzed.ResultsOur results demonstrated that even within the normal auditory threshold, individuals with occupational noise exposure showed lower speech-in-noise scores and higher gap detection threshold and SP/AP values. Speech-in-noise score was correlated SP/AP value. The electrocochleography values showed no significant correlation with the gap detection threshold.ConclusionThe result confirmed that noise-induced cochlear synaptopathy occurs in humans with occupational noise exposure. However, they also implied that the mechanism of cochlear synaptopathy in humans is more complicated than that in experimental animals.

Low stroke incidence in the TEMPiS telestroke network during COVID-19 pandemic – effect of lockdown on thrombolysis and thrombectomy

Background During the COVID-19 pandemic emergency departments have noted a significant decrease in stroke patients. We performed a timely analysis of the Bavarian telestroke TEMPiS “working diagnosis” database. Methods Twelve hospitals from the TEMPiS network were selected. Data collected for January through April in years 2017 through 2020 were extracted and analyzed for presumed and definite ischemic stroke (IS), amongst other disorders. In addition, recommendations for intravenous thrombolysis (rtPA) and endovascular thrombectomy (EVT) were noted and mobility data of the region analyzed. If statistically valid, group-comparison was tested with Fisher’s exact test considering unpaired observations and ap-value < 0.05 was considered significant. Results Upon lockdown in mid-March 2020, we observed a significant reduction in recommendations for rtPA compared to the preceding three years (14.7% [2017–2019] vs. 9.2% [2020], p = 0.0232). Recommendations for EVT were significantly higher in January to mid-March 2020 compared to 2017–2019 (5.4% [2017–2019] vs. 9.3% [2020], p = 0.0013) reflecting its increasing importance. Following the COVID-19 lockdown mid-March 2020 the number of EVT decreased back to levels in 2017–2019 (7.4% [2017–2019] vs. 7.6% [2020], p = 0.1719). Absolute numbers of IS decreased in parallel to mobility data. Conclusions The reduced stroke incidence during the COVID-19 pandemic may in part be explained by patient avoidance to seek emergency stroke care and may have an association to population mobility. Increasing mobility may induce a rebound effect and may conflict with a potential second COVID-19 wave. Telemedical networks may be ideal databases to study such effects in near-real time.

Multifactorial Model Of Attitudes Towards Appearance: Empirical Investigations

This study is focusing on interrelations between attitudes towards Appearance (AP), value functional significance of AP, and life satisfaction. The study is aimed at gaining a theoretical foundation of the developed Multifactorial Model of Attitudes towards AP as well as at empirical testing of the interrelations between the single factors of the model and their combined influence on life satisfaction. It is hypothesised that a different combination of the single factors of the Multifactorial Model of Attitudes towards AP has a different impact on life satisfaction. The participants were 86 females and 86 males aged between 17 and 25 years. The inventory “Diagnostics of Real Structure of Personality Value Orientations” (Bubnova, 1999) the questionnaires “Significance of AP in Various Life Situations” (Labunskaya & Serikov, 2018), Attitudes towards AP, Satisfaction and Concern” (Labunskaya & Kapitanova, 2016), the AP Perfectionism Scale (APPS) (Srivastava, 2009) and the Life Satisfaction Index developed by Neugarten and adopted by N. V. Panina (1993) were administered. The factorial analysis revealed two types of interrelations that relate to different components of the developed Multifactorial Model of Attitudes towards AP. The results showed that considering AP as a value, attributing of higher significance to AP in various interaction contexts as well as higher AP perfectionism lead to lower life satisfaction.

Insulator Detection Method in Inspection Image Based on Improved Faster R-CNN

The detection of insulators in power transmission and transformation inspection images is the basis for insulator state detection and fault diagnosis in thereafter. Aiming at the detection of insulators with different aspect ratios and scales and ones with mutual occlusion, a method of insulator inspection image based on the improved faster region-convolutional neural network (R-CNN) is put forward in this paper. By constructing a power transmission and transformation insulation equipment detection dataset and fine-tuning the faster R-CNN model, the anchor generation method and non-maximum suppression (NMS) in the region proposal network (RPN) of the faster R-CNN model were improved, thus realizing a better detection of insulators. The experimental results show that the average precision (AP) value of the faster R-CNN model was increased to 0.818 with the improved anchor generation method under the VGG-16 Net. In addition, the detection effect of different aspect ratios and different scales of insulators in the inspection images was improved significantly, and the occlusion of insulators could be effectively distinguished and detected using the improved NMS.

Faktor-faktor yang mempengaruhi kecemasan ibu hamil trimester III

The purpose of this study was to determine the factors thatinfluence on anxiety of pregnancy third trimester. This research is adescriptive cross-sectional design. The sampling technique used isconsecutive sampling with the total sample 61 respondents. The analysisused is independent t test. The results showed the factors that influenceon anxiety of pregnancy third trimester is the support of husband with ap value of 0,048 (p <0.05), while the age of mother, education level,occupation, gravidity and physical exercise can not be influence relatedto anxiety of pregnancy third trimester with p> 0,05. Conclusions factorsthat influence anxiety third trimester pregnant women isthe support ofhusband.