Narrow Results

Manually inspecting bugs to determine their severity is often an enormous but essential software development task, especially when many participants generate a large number of bug reports in a crowdsourced software testing context. Therefore, boosting the capabilities of methods of predicting bug report severity is critically important for determining the priority of fixing bugs. However, typical classification techniques may be adversely affected when the severity distribution of the bug reports is imbalanced, leading to performance degradation in a crowdsourcing environment. In this study, we propose an enhanced oversampling approach called CR-SMOTE to enhance the classification of bug reports with a realistically imbalanced severity distribution. The main idea is to interpolate new instances into the minority category that are near the center of existing samples in that category. Then, we use an extreme learning machine (ELM) — a feedforward neural network with a single layer of hidden nodes — to predict the bug severity. Several experiments were conducted on three datasets from real bug repositories, and the results statistically indicate that the presented approach is robust against real data imbalance when predicting the severity of bug reports. The average accuracies achieved by the ELM in predicting the severity of Eclipse, Mozilla, and GNOME bug reports were 0.780, 0.871, and 0.861, which are higher than those of classifiers by 4.36%, 6.73%, and 2.71%, respectively.

A total of 116 surgically treated patients with unstable fractures of the thoracic and lumbar spines were subjected to this study on basis of the simple radiographic and CT findings of the injured spinal column and neurological changes at the injured cord and/or roots level. Among them 50 patients were paraplegics and 66 patients were non-paraplegics. Spine fracture patterns shown on axial CT images were classified into five types on the basis of the fracture severity of vertebral body associating the canal compromise by the encroached fracture fragments from middle column and posterior element. Type I: vertical linear fracture through mid-anterior and posterior elements; Type II: retropulsed fragment in the canal with intact posterior element; Type III: retropulsed fragment in the canal with fracture of the posterior element; Type IV: severe comminution of body and disruption of posterior element around the canal; Type V: fracture-dislocation of comminuted vertebral body and neural arch (with or without double margin sign and with or without vacant facet sign). Displacement of vertebral body on lateral plane radiograms showed significant difference ($p$ < 0.001) between the non-paralytics and paralytics, but there were no differences in kyphotic angles and anterior body height loss between the two groups. Neurological injury was highly complicated in cases of the fracture-dislocation (20 out of 22 patients: 90.9%). Unstable fracture which occurred in the thoracic level showed high incidence of neurological injuries [24 out of 28 patients (85.7%)]; complete paralysis in 20 (71.4%) out of 28 patients in comparison with that of the thoracolumbar and lumbar fractures. Anteroposterior (AP) diameter of the compromised neural canal and percentile surface area of the compromised canal showed significant differences between the paralytics and non-paralytics (canal diameter: $p$ < 0.05, canal compromise: $p$ < 0.05). Neural deficit was highly complicated in type IV and V fractures. In conclusion, it was found that clinical neurological assessment and CT-based fracture classification were the valid approaches in managing the fractured spine.

In order to highlight the cardiac sounds or phonocardiogram (PCG) signals analysis according to their added murmur importance, we try to apply the wavelet transform in its multi resolution analysis version. We then look for reconstruction error between the original signal and the synthesized signal. In this case, the original PCG signal is decomposed over seven levels and the seventh detail of decomposition is considered as the synthesized signal. According to the results we obtain, the reconstruction error can be considered as an important parameter in the classification and discrimination of the pathological severity of the PCG signals.

Knee osteoarthritis (KOA) changes the force applied on the lower extremities. The purpose of this study was to investigate the relationship between various severity of KOA and the forces applied to the lower limb during walking. Sixty eight limbs were divided into three groups of mild, moderate and severe KOA and a healthy normal group according to the Kellgren–Lawrence scale. The subjects walked with a self-selected speed to collect five successful trials. The components of ground reaction forces i.e., medio-lateral (ML), first peak of antero-posterior (AP1), second peak of antero-posterior (AP2), first peak of vertical (VP1), second peak of vertical (VP2) and vertical valley (V.V) were collected. AP1 and AP2 had decreasing pattern with increasing disease severity. Although ML Peak and VV have shown rising trend from normal people to severe KOA, ML difference was not significant in various groups ($p>0.05$). In addition, the VP1 did not differ significantly among the subjects. In contrast, the VP2 decreased significantly in OA subjects ($p=0.002$). It seems that AP1 and VP2 components are more sensitive to KOA, which may be used to represent severity of knee OA.

The phonocardiogram (PCG) signal is sometimes affected by added parameters that reflect the presence of a specific pathology. The intensity or the energy of the signal is one of the most reliable parameters when studying cardiac severity. Yet, in a pathological electrophysiological and audio signal, the severity information does not fully remain in the intensity or energy, but in other variables. In this paper, we will discuss the ability of a time-frequency parameter to discriminate, separate, and monitor the pathological cardiac severity levels. We studied 14 PCG signal from eight pathologies, six of them contain clicks (reduce murmurs), and eight murmur PCG signals with four different cardiac severity levels. We then calculated the entropy of approximation coefficients (EAC) from a discrete wavelet transform (DWT) analysis, to differentiate the PCG signals with clicks from those with murmurs and to assess the cardiac severity evolution. Since the entropy EAC is also related to the signal’s intensity (energy), we compared it to the energetic ratio (ER) evolution, a parameter widely used for PCG signals discrimination and classification, which revealed that the EAC provied better results for the paper' purposes.

The occasional “strike hard” campaigns against crime launched by the Chinese government provide an opportunity to isolate the separate effects of severity and certainty of punishment on the crime rate. The “strike hard” campaigns increase the severity of the punishment but keep the certainty of the punishment unchanged. We use provincial panel data from 1988 to 2015 to examine the impacts of the two strategies on the crime rate with pooled mean group models. The empirical results show that a significant decrease in crime rates is associated with greater certainty of detection, but greater severity has no significant effect. A 1% increase in the detection rate (a measurement of certainty) predicts about 2.7% lower crime rate. The results are robust even after considering the endogenous nature of punishment policies and controlling for the measurement error in the officially reported data.

Background: Congenital hand differences (CHD) exhibit enormous diversity and heterogeneity. Surgeons and parents often have different concepts of severity, making things difficult during parental consultation. This study aims to align surgeon/parental views on the severity of the child’s CHD using a novel severity classification.

Methods: Parents of affected children were asked to score the severity of their child’s abnormality pre- and post-consultation using a subjective scale (1–4) without any explanation. Furthermore, parents were asked to rate their concerns about the future function and appearance of their child’s hand condition using a similar scale of 1–4. They were then asked to rate the severity of the CHD post-consultation and three months post-operatively following explanation of the 4-point scale, as follows: 1 = treatment possible to normal; 2 = treatment possible to near normal; 3 = treatment possible but always some hand differences; 4 = treatment not possible. The surgeon also independently scored all children using his perception of the scale.

Results: Forty-three children with a range of CHD were recruited into the sample. Linear weighted kappa analyses comparing inter-rater agreement showed no agreement between surgeon and parents during the initial scoring without any explanations. However, with explanations added, agreement rose significantly (kappa = 0.437 post-consultation and kappa = 0.706 three months post-op). No correlation was found between severity with both appearance and function (r = 0.277 and r = −0.184, respectively).

Conclusions: This study demonstrated that the use of a simple scoring system was able to improve parental understanding of the severity and prognosis of CHD. The system demonstrated a good correlation between surgeon and parents. Such a scoring system can be easily utilised in the outpatient department to manage expectations and reduce anxiety.

Background: Obstetrician and gynecologist are one of the contributors in patient care who are susceptible to contracting coronavirus-19 infection. Emergency measures for maternal field are high, while gold standard examination for COVID-19 takes long time with false negative rate. The case fatality rate of COVID-19 among health workers in Indonesia is reported to be high. We want to know epidemiological, clinical, and occupational characteristics of various degrees of COVID-19 severity and create scoring model to predict COVID-19 severity in ob/gyn doctors in Indonesia.

Method: This is a descriptive analytic study using a cross-sectional approach. Consecutive sampling was taken from ob/gyn doctors infected with COVID-19 and analyses used were Chi-Square and Mann-Whitney U tests. A scoring model is created and using receiver operating characteristic (ROC) curves, to determine the predictive ability of the scoring model and the cutoff value to COVID-19 severity, then tested for sensitivity and specificity.

Result: The mean age of the respondents was 38.2 ± 9.8 and 48.7% were male. Sixty-one percent respondents experienced mild symptoms, infected while on duty (46.1%), and 59% had nuclear family member infected with COVID-19. Age group ($p$ = 0.000), number of infection ($p$ = 0.000), vaccination status ($p$ = 0.010), comorbidities ($p$ = 0.023), and working hours ($p$ = 0.002) were significantly different on the COVID-19 severity. Area-under-curve of scoring model was 75.2% and 93.4%. The cutoff value was 10.5 points for between asymptomatic and mild degree (sensitivity 54.2% and specificity 77.8%) and 12.5 points between mild and moderate degree (sensitivity 83.3% and specificity 95.8%) respectively.

Conclusion: The developed scoring model can facilitate prediction of COVID-19 severity in ob/gyn doctors, with asymptomatic (score of < 10.5 points), mild degree (score of 10.5–12.5 points), and moderate degree (score of > 12.5 points).

This paper gives a performance comparison in terms of Root mean square error (RMSE) of the six regression techniques used to predict the Parkinson disease severity score. People affected by Parkinson disease suffer various muscular impairments like gait, speech etc. The severity of the disease is generally assessed by the clinicians by observing the different muscular functions of the affected people or by performing scans of the brain. This paper focusses on predicting the disease severity using features of speech signal and performing regression on these features. The features used in the prediction are the phonation features extracted from voice samples of both Parkinson disease affected people and healthy people. The 14 phonation features extracted include the frequency variability features jitter and its other variants, the energy variability features shimmer and its other variants, the mean auto correlation of the pitch frequencies, harmonicity features harmonic to noise ratio and noise to harmonic ratio. The six regression techniques used to predict the severity score are the Linear, Stepwise, Lasso, Ridge regression, prediction using Neural network model and Classification and Regression trees (CART). The trained regression model is validated using the $k$-fold cross-validation method with $k$ values three, five, seven and ten and also using the hold out validation model in which the hold out value is taken to be 0.3. The results obtained from the six regression techniques is then compared and it shows that the severity score prediction using Neural network model provides the least RMSE of 1.5 followed by 1.8 using the CART regression technique.

Much has been learnt about severe acute respiratory syndrome Coronavirus 2 (SARS-CoV-2) since the beginning of the Coronavirus disease 2019 (COVID-19) pandemic, including its clinical manifestations, diagnosis, and management. Unlike its zoonotic predecessor SARS-CoV which was largely a symptomatic disease where fever was a hallmark, a significant proportion of SARS-CoV-2 infections can be asymptomatic (40%), while severe disease (requiring oxygen supplementation or ventilatory support) occurs in approximately 20%, and mortality in about 2% of infected patients. Extra-pulmonary COVID-19 manifestations are also more protean, compared to SARS. Supportive care is the mainstay of treatment for most patients, but for those who progress to severe COVID-19, antivirals such as remdesivir and immunomodulatory treatment (such as corticosteroids or the JAK-inhibitor, baricitinib) may improve outcomes. While further advances in the management of COVID-19 are anticipated (including novel therapies), prevention of infection through public health measures (including vaccination), will remain as vital facets in confronting this pandemic.

The frequency and severity of road accidents are closely connected to geographical factors, including geographic region, landform, road condition and weather. Based on the statistic of accident data in 2013, this paper studies the geographical distribution of road accidents in China, as well as the correlation between geographic factors and crash severity. The results indicate that the western district of China has a higher mortality rate than other areas. Specific geographic conditions may lead to relevant types of crashes, e.g. single vehicle crashes are in relation to specific landform of crash sites. And for the total crashes, Chi-square test reveals that night time, high way, mountainous area, curve road line, national road and low visibility significantly relate to nonfatal/fatal crashes. Among various factors influenced by climate, road surface covered with ice and snow has the highest mortality. Considering practical active safety system and driver assistance system in vehicles, this paper also discusses some corresponding countermeasures for special crashes. The research findings provide useful guidance oriented to different geographic area for the relevant research of traffic safety.