A study of dealing class imbalance problem with machine learning methods for code smell severity detection using PCA-based feature selection technique.

Detecting code smells may be highly helpful for reducing maintenance costs and raising source code quality. Code smells facilitate developers or researchers to understand several types of design flaws. Code smells with high severity can cause significant problems for the software and may cause challenges for the system's maintainability. It is quite essential to assess the severity of the code smells detected in software, as it prioritizes refactoring efforts. The class imbalance problem also further enhances the difficulties in code smell severity detection. In this study, four code smell severity datasets (Data class, God class, Feature envy, and Long method) are selected to detect code smell severity. In this work, an effort is made to address the issue of class imbalance, for which, the Synthetic Minority Oversampling Technique (SMOTE) class balancing technique is applied. Each dataset's relevant features are chosen using a feature selection technique based on principal component analysis. The severity of code smells is determined using five machine learning techniques: K-nearest neighbor, Random forest, Decision tree, Multi-layer Perceptron, and Logistic Regression. This study obtained the 0.99 severity accuracy score with the Random forest and Decision tree approach with the Long method code smell. The model's performance is compared based on its accuracy and three other performance measurements (Precision, Recall, and F-measure) to estimate severity classification models. The impact of performance is also compared and presented with and without applying SMOTE. The results obtained in the study are promising and can be beneficial for paving the way for further studies in this area.

EduNet: A New Video Dataset for Understanding Human Activity in the Classroom Environment.

Human action recognition in videos has become a popular research area in artificial intelligence (AI) technology. In the past few years, this research has accelerated in areas such as sports, daily activities, kitchen activities, etc., due to developments in the benchmarks proposed for human action recognition datasets in these areas. However, there is little research in the benchmarking datasets for human activity recognition in educational environments. Therefore, we developed a dataset of teacher and student activities to expand the research in the education domain. This paper proposes a new dataset, called EduNet, for a novel approach towards developing human action recognition datasets in classroom environments. EduNet has 20 action classes, containing around 7851 manually annotated clips extracted from YouTube videos, and recorded in an actual classroom environment. Each action category has a minimum of 200 clips, and the total duration is approximately 12 h. To the best of our knowledge, EduNet is the first dataset specially prepared for classroom monitoring for both teacher and student activities. It is also a challenging dataset of actions as it has many clips (and due to the unconstrained nature of the clips). We compared the performance of the EduNet dataset with benchmark video datasets UCF101 and HMDB51 on a standard I3D-ResNet-50 model, which resulted in 72.3% accuracy. The development of a new benchmark dataset for the education domain will benefit future research concerning classroom monitoring systems. The EduNet dataset is a collection of classroom activities from 1 to 12 standard schools.

Women and Tobacco Use: Discrepancy in the Knowledge, Belief and Behavior towards Tobacco Consumption among Urban and Rural Women in Chhattisgarh, Central India.

BACKGROUND: Tobacco consumption has become pandemic, and is estimated to have killed 100 million people in the 20th century worldwide. Some 700,000 out of 5.4 million deaths due to tobacco use were from India. The era of global modernization has led to an increase in the involvement of women in tobacco consumption in the low income and middle-income countries. Tobacco consumption by females is known to have grave consequences. OBJECTIVES: To assess: (1) the tobacco use among urban and rural women; (2) the discrepancy in the knowledge, belief and behavior towards tobacco consumption among urban and rural women in Durg-Bhilai Metropolitan, Chhattisgarh, Central India. MATERIALS AND METHODS: The study population consisted of 2,000 18-25 year old young women from Durg-Bhilai Metropolitan, Chhattisgarh, Central India, from both urban and rural areas. Data were collected using a pretested, anonymous, extensive face to face interview by a female investigator to assess the tobacco use among women and the discrepancy in the knowledge, belief and behavior towards tobacco consumption among urban and rural individuals. RESULTS: The prevalence of tobacco use was found to be 47.2%. Tobacco consumption among rural women was 54.4% and in urban women was 40%. The majority of the women from urban areas (62.8%) were smokers whilst rural women (77.4%) showed preponderance toward smokeless tobacco use. Urban women had a better knowledge and attitude towards harms from tobacco and its use than the rural women. Women in rural areas had higher odds (1.335) of developing tobacco habit than the urban women. CONCLUSIONS: Increased tobacco use by women poses very severe hazards to their health, maternal and child health, and their family health and economic well-being. Due to the remarkably complex Indian picture of female tobacco use, an immediate and compulsory implementation of tobacco control policies laid down by the WHO FCTC is the need of the hour.

Patterns of left ventricular hypertrophy in chronic kidney disease: an echocardiographic evaluation.

BACKGROUND: We evaluated the chronic kidney disease (CKD) patients having different degree of uremia for the prevalence of Left Ventricular Hypertrophy (LVH), different patterns of left Ventricular Hypertrophy by echocardiographic variables to define the most sensitive and powerful predictor of cardiovascular disease (CVD) and premature morbidity and mortality. METHODS: We used clinical and biochemical data from the prospective study done by us to evaluate "The Echocardiographic assessment of cardiac functions in patients with chronic kidney disease". The diagnosis of CKD was made on the basis of serum creatinine (sCr) concentration of more than 1.5 mg/dl, persistent and with no evidence of recovery over a period of 3 months. Glomerular filtration rate (GFR) was calculated by the Modification of Diet in Renal Disease (MDRD) equation and cut-off for CKD was taken to be < 60 ml/min/1.73 m2 as per existing guidelines. The study population consisted of a total of 75 subjects divided into three groups of 25 subjects each, all between the age of 20-65 yrs: GROUP A: Healthy normal controls (sCr < 1.5 mg/dl); GROUP B: Patients with mild to moderate CKD (sCr 1.5 - 6.0 mg/dl); GROUP C: Patients with severe CKD (sCr > 6.0 mg/dl). RESULTS: A progressive rise in prevalence of LVH was observed with the severity of kidney disease from 64% (mild/ moderate CKD group) to 96% (severe CKD group) and higher prevalence of LVH in females than males in the severe CKD group. The mean LVMI in both the groups of CKD was significantly higher than the healthy controls (76.62 +/- 10.97). Also, mean LVMI in severe CKD (139.23 +/- 17.47) patients was significantly higher than in mild/moderate CKD (114.91 +/- 15.20) patients. The prevalence of concentric remodeling in both the CKD groups was alike (20%). While that of concentric hypertrophy in severe CKD patients (68%) was significantly higher than in mild/moderate CKD group (40%) (p < 0.05), but no significant difference was observed for eccentric pattern of hypertrophy between the two CKD groups. This suggests that concentric hypertrophy is more prevalent in CKD patients. CONCLUSIONS: The mean left ventricular mass index (LVMI) showed a proportionate increase with the severity of renal failure and a progressive rise with increase in severity of disease. Patients of CKD groups revealed occurrence of concentric remodeling which is a predictor of high vulnerability for progressing into concentric and eccentric hypertrophy. Hence early medical intervention may reverse the concentric remodeling, thereby preventing the advancement to concentric or eccentric LVH.