• Journal of Information Processing Systems
• /
• v.10 no.2
• /
• pp.314-333
• /
• 2014

When analyzing default predictions in real estate companies, the number of non-defaulted cases always greatly exceeds the defaulted ones, which creates the two-class imbalance problem. This lowers the ability of prediction models to distinguish the default sample. In order to avoid this sample selection bias and to improve the prediction model, this paper applies a minority sample generation approach to create new minority samples. The logistic regression, support vector machine (SVM) classification, and neural network (NN) classification use an imbalanced dataset. They were used as benchmarks with a single prediction model that used a balanced dataset corrected by the minority samples generation approach. Instead of using prediction-oriented tests and the overall accuracy, the true positive rate (TPR), the true negative rate (TNR), G-mean, and F-score are used to measure the performance of default prediction models for imbalanced dataset. In this paper, we describe an empirical experiment that used a sampling of 14 default and 315 non-default listed real estate companies in China and report that most results using single prediction models with a balanced dataset generated better results than an imbalanced dataset.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.389-396
• /
• 2022

Smartphones are growing more susceptible as technology develops because they contain sensitive data that offers a severe security risk if it falls into the wrong hands. The Android OS includes permissions as a crucial component for safeguarding user privacy and confidentiality. On the other hand, mobile malware continues to struggle with permission misuse. Although permission-based detection is frequently utilized, the significant false alarm rates brought on by the permission-based issue are thought to make it inadequate. The present detection method has a high incidence of false alarms, which reduces its ability to identify permission-based attacks. By using permission features with intent, this research attempted to improve permission-based detection. However, it creates an excessive number of features and increases the likelihood of false alarms. In order to generate the optimal number of features created and boost the quality of features chosen, this research developed an intersection feature approach. Performance was assessed using metrics including accuracy, TPR, TNR, and FPR. The most important characteristics were chosen using the Correlation Feature Selection, and the malicious program was categorized using SVM and naive Bayes. The Intersection Feature Technique, according to the findings, reduces characteristics from 486 to 17, has a 97 percent accuracy rate, and produces 0.1 percent false alarms.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.350-358
• /
• 2021

In modern years, the performance of the students is analysed with lot of difficulties, which is a very important problem in all the academic institutions. The main idea of this paper is to analyze and evaluate the academic performance of the college students with bipolar disorder by applying data mining classification algorithms using Jupiter Notebook, python tool. This tool has been generally used as a decision-making tool in terms of academic performance of the students. The various classifiers could be logistic regression, random forest classifier gini, random forest classifier entropy, decision tree classifier, K-Neighbours classifier, Ada Boost classifier, Extra Tree Classifier, GaussianNB, BernoulliNB are used. The results of such classification model deals with 13 measures like Accuracy, Precision, Recall, F1 Measure, Sensitivity, Specificity, R Squared, Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, TPR, TNR, FPR and FNR. Therefore, conclusion could be reached that the Decision Tree Classifier is better than that of different algorithms.

• Genomics & Informatics
• /
• v.9 no.2
• /
• pp.59-63
• /
• 2011

Obesity provokes many serious human diseases, including various cardiovascular diseases and diabetes. Body mass index (BMI) is a highly heritable trait that is broadly used to diagnose obesity. To identify genetic loci associated with obesity in Asians, we conducted a genome-wide association study (GWAS) of a population of Korean adults (n=6,742, age 40~60 years) and detected six BMI risk loci (TNR, FAM124B, RGS12, NFE2L3, MC4R and FTO) having p< $1{\times}10^{-5}$. However, in the replication study, only melanocortin 4 receptor gene (MC4R) (rs9946888, p=$4.58{\times}10^{-7}$) was replicated with marginal significance (p<0.05) in the second cohort (n=5,102, age 40~60 years). This study indicates that each locus associated with BMI has very weak genetic effect.

• Journal of Veterinary Clinics
• /
• v.34 no.1
• /
• pp.34-38
• /
• 2017

The aims of the present study were to determine the weaning time for adoption of kittens, and to evaluate the fetal growth rate during pregnant in free-roaming cats. This study was conducted on three pregnant free-roaming cats (one feral cat and two stray cats). Radiography and ultrasonography were performed on the feral cat and on one of the stray cats. In the feral cat, fetal head diameter was measured once during pregnancy to determine the cesarean section (C-sec) time. In the stray cat, serial fetal head diameter was measured from capture to parturition. The body weight of the feral cat's kittens was measured from 4 weeks postpartum because of their wildness. That of the stray cats' kittens was measured immediately after birth. In the feral cat, scheduled C-sec was performed at predicted parturition day by measurement of head diameter, and six healthy kittens were delivered. The stray cats had five and six kittens by natural delivery, respectively. In the body weight gain of feral and stray cat's kittens, two female kittens of the feral cat lost weight rapidly after they were separated from their mother, so they were returned to their mother for 1 more week. After that, the female kittens grew up without difficulty. Body weight gain of the ten kittens born to the two stray cats consistently increased, by approximately 14 g every day, until they were adopted. The body weight of kittens born by natural delivery was on average 77.5 g greater than that of kittens born by C-sec. However, the gap decreased with time. During the stray cat's pregnancy, fetal head diameter increased by 0.042 cm every day. Maximum head size before parturition was 2.43 cm. These results indicate that the weaning time for adoption of kittens was 5-week-old postpartum.

• Korean Journal of Veterinary Service
• /
• v.45 no.4
• /
• pp.249-252
• /
• 2022

Giardiasis is widespread all over the world, and it is a disease that causes both acute and chronic digestive symptoms. It is zoonotic disease that affects animals and humans. There are few studies on giardiasis in stray cats due to difficulties in catching and sampling. Therefore, this study evaluated the prevalence of giardiasis in stray cats in the Daejeon city because of increasing interest as zoonotic disease. The specimens were the feces of stray cats captured for the neutering project (TNR) in Daejeon; 30 fecal samples were collected from 2021 to 2022 in each of 5 districts in Daejeon. A total of 150 samples were collected. All samples were tested for giardiasis using the Giardia SNAP kit (SNAP^Ⓡ test, IDEXX Laboratories. Inc., Westbrook, ME). The overall prevalence rate was 46 out of 150 cats (30.7%). By age, 25 out of 71 juvenile cats (35.2%) were positive, and 21 out of 79 adult cats (26.6%) were positive. A total of 19 out of 69 cats (27.5%) with diarrhea were positive, and 27 out of 81 asymptomatic cats (33.3%) were positive. For gender, 38 out of 99 females (38.4%) were positive, and 8 out of 51 males (15.7%) were positive. The positive rate of giardiasis in stray cats was over 30%, which is high compared to other research results. It is necessary to increase the public's awareness of the value of deworming stray cats and the sanitation of people who have come into contact with them.

• The Plant Pathology Journal
• /
• v.35 no.6
• /
• pp.644-653
• /
• 2019

The genetic variability of 'Candidatus Liberibacter asiaticus' (CLas) population associated with huanglongbing (HLB) disease of citrus in North Eastern (NE) region of India, a geographically locked region, and home for the diversity of many citrus species was analyzed on the basis of tandem repeat numbers (TRN) in variable CLIBASIA_01645 genomic loci. Fifty-five CLas strains sampled from different groves of NE Hill (NEH) region of India were in single amplicon group, but there was remarkable genetic variability in TRNs. The TRN in HLB-associated CLas strains varied from 0-21 and two novel repeat motifs were also identified. Among the NE population of CLas, TRN5 and TRN9 were most frequent (total frequency of 36.36%) followed by TRN4 (14.55%) and TRN6, TNR7 with a frequency of 12.73% each. Class II type CLas genotypes (5 < TRN ≤ 10) had highest prevalence (frequency of 60.00%) in the samples characterized in present study. Class I (TRN ≤ 5) genotypes were second highest prevalent (29.09%) in the NEH region. Further analysis of genetic diversity parameters using Nei's measure (H value) indicated wide genetic diversity in the CLas strains of NE India (H value of 0.58-0.86). Manipur CLas strains had highest genetic variability (0.86) as compared to Eastern, Southern and Central India. The R₁₀ values (TRN ≤ 10/TRN > 10) of NE CLas population was 10.43 (73/7), higher from other regions of India. Present study conclusively reported the occurrence of high genetic variability in TRN of CLas population in North East Indian citrus groves which have evolved to adapt to the specific ecological niche.