Two machine learning approaches are introduced for text segmentation. The first approach is based on inductive learning in the form of a decision tree and the second uses the Naïve Bayes technique. A set of training data is generated from a wide category of compound text image documents for learning both the decision tree and the Naive Bayes Classifier (NBC). The compound documents used for generating the training data include both machine printed and handwritten texts with different fonts and sizes. The 18-Discrete Cosine Transform (DCT) coefficients are used as the main feature to distinguish texts from images. The trained decision tree and the Naive Bayes are tested with unseen documents and very promising results are obtained. Although the later method is more accurate and computationally faster, Finally, the results obtained from the proposed approaches are compared and contrasted with one wavelet based approach and it is illustrated that both methods presented in this paper are more effective.

The way that students approach their learning plays an important role in determining the outcome of any educational endeavor. Recent researches have made it clear that approaches to studying and perceptions of teaching are two of the most direct influences on the quality of student learning. Learning approaches of students have been found to be influenced by a number of factors, such as teaching characteristics, departmental characteristics, and assessment methods. Surface, deep, and strategic are the three basic learning approaches which are identified by researchers in various Studies.One of the major concepts to emerge from researches in higher education was the idea that students can take different approaches to learning. These approaches are not stable traits in individuals, although some students will tend towards taking a deep approach while others will tend towards taking a surface approach. Rather, it is suggested that good teaching can influence students to take a deep approach, while poor teaching in the widest sense can pressure students to take a surface approach.

Deep learning technology, philosophical challenges and approaches Abstract The unprecedented human’ s advancement in generating and storing piles of data, and exploiting such large amounts of data for building reasoning machines has manifested as a technology known as “ deep learning” . This technology is inspired by the brain’ s connectivity structure and is empowered by deep artificial neural networks. In spite of numerous benefits offered by their great power in reasoning like experts or creating things like skillful people, this technology imposes some ethical challenges to human’ s life. This article tries to present the ethical challenges of deep learning technology that threaten humanity and tries to address them by employing a rational-philosophical approach. Although deep learning technology imposes several ethical challenges on our lives, it is still possible to benefit from big data without sacrificing our ethical values provided we gain awareness about and preparation against such challenges.

Background: Breast cancer is considered one of the most common cancers in women caused by various clinical, lifestyle, social, and economic factors. Machine learning has the potential to predict breast cancer based on features hidden in data. Objective: This study aimed to predict breast cancer using different machinelearning approaches applying demographic, laboratory, and mammographic data. Material and Methods: In this analytical study, the database, including 5, 178 independent records, 25% of which belonged to breast cancer patients with 24 attributes in each record was obtained from Motamed cancer institute (ACECR), Tehran, Iran. The database contained 5, 178 independent records, 25% of which belonged to breast cancer patients containing 24 attributes in each record. The random forest (RF), neural network (MLP), gradient boosting trees (GBT), and genetic algorithms (GA) were used in this study. Models were initially trained with demographic and laboratory features (20 features). The models were then trained with all demographic, laboratory, and mammographic features (24 features) to measure the effectiveness of mammography features in predicting breast cancer. Results: RF presented higher performance compared to other techniques (accuracy 80%, sensitivity 95%, specificity 80%, and the area under the curve (AUC) 0. 56). Gradient boosting (AUC=0. 59) showed a stronger performance compared to the neural network. Conclusion: Combining multiple risk factors in modeling for breast cancer prediction could help the early diagnosis of the disease with necessary care plans. Collection, storage, and management of different data and intelligent systems based on multiple factors for predicting breast cancer are effective in disease management.