Sharif Digital Repository

Studies show that a large proportion of sent emails are spam. Spam is one of the major problems of e-mail users that result in wasting time and cost. To overcome this problem different ways are used, one of the best ways is detecting spam based on their contents. Separating legitimate e-mails and spam within their contents can be categorized as text classification. So machine-learning approaches are extremely applied in text classification, that machine-learning algorithms can be used for spam classification. However, in the majority of these algorithms, training phase is in a batch. Whereas using incremental learning algorithms is preferred in many applications, especially spam detections.... 

Identifying driving behaviors and building an efficient and accurate driving behavior recognition model is of paramount importance for improving driving safety. Nowadays, with the ubiquity of smartphone sensors, many researchers are using smartphone sensory data to create models which forecast driving behaviors. This research introduces a logit model that predicts nine types of driving events using accelerometer and gyroscope sensors with an accuracy of 76 percent  

Nowadays, bilayer sheets are increasingly used in various industries due to high mechanical properties, high corrosion resistance and low weight. Hence, it seems important to investigate welding of these materials. The main object of this study is to investigate mechanical properties and microstructure of friction stir butt welded Al-Cu bilayer sheets. For this purpose, tensile tests, microhardness measurements, metallographic images, SEM, EDS and XRD analyses have been carried out from the joints. The results show that contact condition between the shoulder and bilayer material (slipping or sticking), plays an important role in material flow during welding and weld quality. Also the...