Sharif Digital Repository

Collaborative fltering (CF) is one of the best and widely employed approaches in Recommender systems (RS). This approach tries to fnd some latent features for users and items so it would predict user rates with these features. Early CF methods used matrix factorization to learn users and items latent features. But these methods face cold start as well as sparsity problem. Recent years methods employ side information along with rating matrix to learn users and items latent features. On the other hand, deep learning models show great potential for learning effective representations especially when auxiliary information is sparse. Due to this feature of deep learning, we use deep learning to... 

Wireless sensor networks (WSNs) can be used in a variety of applications. The prime shortcoming of these networks is their energy constraint. The main energy consumer in a sensor node is its radio transmitter. Therefore data prediction is one of the most effective methods to reduce the data transmission rate. By data prediction, a large amount of energy is saved; which results in the longevity of the network life. Environmental variations almost have similar effects on different sensor sources in a sensor device. So, considering the correlation between different sources reduces the noise impact and increases data prediction accuracy. In this thesis, we use temporal and multisource... 

The World Wide Web has been experiencing a massive growth regarding its content and users in recent years; therefore the need for effective means of accessing and processing available items has attracted a wide range of researchers and industries. Recommender systems has emerged to help both users to find what they may be interested in and the producers to sell their products more efficiently. As the number of these techniques grow, the need to evaluate them properly increases as well. However the proposed evaluation metrics are very diverse and often inconsistent with each other. Although there had been immense research in this field, there is no united and proper approach for evaluation of... 

Nowadays, recommender systems have become powerful tools that engage users in an online manner, over the Internet. Collaborative filtering (CF) is a well established method for building recommender systems and has been applied to several applications. While CF has its advantages,its use is hindered by challenges such as low accuracy for new users (newcomers). With the growth of online social networks, networkbased recommender systems emerged. These systems take advantage of the information available in social networks and the user’s past activity to recognize user behavior and recommend items that are more relevant to each user. One of the most important advantages of network-based... 

In this thesis the usage of probabilistic reasoning in collaborative filtering is investigated. The problem of predicting users' rating is formulated as a Bayesian decision problem and a generative probabilistic model is used in order to find the optimal decision. Two different probabilistic models are considered: user based model and rating based model. In user based model prediction of ratings is based on structural learning of Bayesian networks. In rating based model, we assume a predefined Bayesian network represents the joint distribution over model variables and rating prediction is carried out using McMc inference method. MovieLens dataset is chosen to evaluate and compare the results... 

Blackhole and grayhole attacks have been become two of the major security concerns in mobile ad hoc networks (MANET). To achieve security in MANETs, a lot of mechanisms had been proposed by now. Using intrusion detection systems(IDSs) is one of the important mechanism to reach this goal. Thus, a well-known IDS was chosen and analyzed in this thesis. Furthermore, a collaborative bayesian filter approach for this intrusion detection system was proposed to enhance its performance. Then the performance of this approach was considered. This intrusion detection system was analyzed using stochastic modeling like continuous time markov chain(CTMC), stochastic reward net(SRN) and stochastic... 

Nowadays recommender systems are one of the most important parts of big websites. These systems help users to find their intended items among enormous amounts of data. Traditionally, recommender systems are designed and implemented using different methods such as content based, collaborative and demographic filtering. Each of these methods had some problems that lead to emergence of a new kind of recommender systems called hybrid recommender systems. This kind of recommender systems try to combine the other methods and make them better. In this thesis, we have selected some previous recommender systems and then, we have made a new system by combining and reforming them. The resulted... 

Recommender systems are in the center of network science and are becoming increasingly important in individual business for providing efficient personalized services and products to users. The focus of previous research in the field of recommendation systems were on improving the accuracy of the system through designing more accurate recommendation lists. Recently, the community has been paying attention to diversity and novelty of recommendation list as key characteristics of modern recommender systems. In many cases, novelty and precision do not go in the same direction and the accuracy-novelty dilemma is one of the challenging problems in recommender systems, which needs efforts in... 

Recommender systems are in the center of network science and becoming increasingly important in individual businesses for providing efficient personalized services and products to users. The focus of previous research in the field of recommendation systems was on improving the precision of the system through designing more accurate recommendation lists. Recently, the community has been paying attention to diversity and novelty of recommendation list as key characteristics of modern recommender systems. In many cases, novelty and precision do not go in the same direction and the accuracy-novelty dilemma is one of the challenging problems in recommender systems, which needs efforts in making a... 

in this study we intend to build a recommender system, more specifically We try to build a multi-criteria collaborative filtering. Collaborative filtering is one of the methods used in building of recommender systems. In this study, we use technical attributes to build a recommender system. Technical attributes refer to the attributes which focus on the writing style of the texts. After building the recommender system based on technical attributes, we also build a recommender system based on the conventional criteria in order to make a comparison between these two criteria. Collaborative filtering consists two major categories, namely memory-based and model-based that both of them have been... 

In competitive markets where a product or service is provided by multiple providers, as the telecom market, keeping active users is expected to be less expensive than attracting new users. In this regard, first of all, churning should be predicted for active users, and secondly, proper recommendations should be provided to prevent churning. In this thesis, by modeling customer churn as a response to the recommendations, we study the churn prediction and prevention problem as a recommender system. This model enables us to select the best offer for each user to prevent it from churning.Modeling customer churn in a recommender system introduces new challenges, including delay in observing... 

In recent years, the cosmetics industry has dramatically grown in e-commerce. In e-commerce platforms, where multiple choices are available, an efficient recommender system is required to sort, order, and effectively transfer relevant content or product information to users. Recommender systems have attracted a lot of attention from retailers because they provide consumers with a personalized shopping experience. With technological advancements, this branch of artificial intelligence exhibits great potential in imaging, analysis, classification, and segmentation. Despite the great potential, the academic articles in this field are limited. Therefore, we conducted research in this context, in...