An efficient approach for textual data classification using deep learning.

Text categorization is an effective activity that can be accomplished using a variety of classification algorithms. In machine learning, the classifier is built by learning the features of categories from a set of preset training data. Similarly, deep learning offers enormous benefits for text classification since they execute highly accurately with lower-level engineering and processing. This paper employs machine and deep learning techniques to classify textual data. Textual data contains much useless information that must be pre-processed. We clean the data, impute missing values, and eliminate the repeated columns. Next, we employ machine learning algorithms: logistic regression, random forest, K-nearest neighbors (KNN), and deep learning algorithms: long short-term memory (LSTM), artificial neural network (ANN), and gated recurrent unit (GRU) for classification. Results reveal that LSTM achieves 92% accuracy outperforming all other model and baseline studies.

Trends of contraception among ladies of local population in Pakistan; why, how, when and what?

OBJECTIVE: To analyze trends of use of methods of contraception along with study of impact of various demographic and social factors on contraception in Peshawar, Pakistan. METHODS: A cross-sectional descriptive study with random purposive sampling was conducted at Combined Military Hospital Peshawar, from Mar 2015-Nov 2015. Self-designed questionnaire with demographic details and questions pertinent to contraceptive practices was utilized as study instrument. Females reporting to concerned hospital for contraceptive advice and prescription were distributed with questionnaire and written informed consent form. Formal approval was taken from ethical committee of hospital. Data was analyzed via descriptive analysis (SPSS-21), qualitative data was expressed as frequencies and percentages; quantitative as mean±standard deviation (SD). Main outcome variable i-e contraceptive device used; was cross-tabulated with independent variables. RESULTS: Response rate was 53.2% (n-426). Usage of contraceptive device was as follows; 51.2% Nil, 9.4% barriers, 22.3% oral/injectable hormones, 13.4% IUCDs, 3.8% sterilization. There was a strong relationship between type of contraceptives used and age (p<0.001), client's education (p<0.001), husband's education (p<0.001), number of children (p<0.001), religion (p0.013), socioeconomic class (p<0.001), and religious beliefs about use of contraceptives (p<0.001). More Muslims considered contraception irreligious than non-Muslims (p 0.02). There was no significant impact of husbands' pressure to not to use contraceptives on type of contraception practised (p 0.114). CONCLUSION: Contraceptive devices are under-utilized in the study participants. Multidisciplinary approach should be applied to enhance client education, awareness and counseling to utilize these devices more appropriately and regularly.