International Conference on Ubiquitous Information Management and Communication 

About: International Conference on Ubiquitous Information Management and Communication is an academic conference. The conference publishes majorly in the area(s): Computer science & Wireless sensor network. Over the lifetime, 1611 publications have been published by the conference receiving 8636 citations.

Addressing cold-start problem in recommendation systems

Abstract: Recommender systems for automatically suggested items of interest to users have become increasingly essential in fields where mass personalization is highly valued. The popular core techniques of such systems are collaborative filtering, content-based filtering and combinations of these. In this paper, we discuss hybrid approaches, using collaborative and also content data to address cold-start - that is, giving recommendations to novel users who have no preference on any items, or recommending items that no user of the community has seen yet. While there have been lots of studies on solving the item-side problems, solution for user-side problems has not been seen public. So we develop a hybrid model based on the analysis of two probabilistic aspect models using pure collaborative filtering to combine with users' information. The experiments with MovieLen data indicate substantial and consistent improvements of this model in overcoming the cold-start user-side problem.

Apriori-based frequent itemset mining algorithms on MapReduce

Abstract: Many parallelization techniques have been proposed to enhance the performance of the Apriori-like frequent itemset mining algorithms. Characterized by both map and reduce functions, MapReduce has emerged and excels in the mining of datasets of terabyte scale or larger in either homogeneous or heterogeneous clusters. Minimizing the scheduling overhead of each map-reduce phase and maximizing the utilization of nodes in each phase are keys to successful MapReduce implementations. In this paper, we propose three algorithms, named SPC, FPC, and DPC, to investigate effective implementations of the Apriori algorithm in the MapReduce framework. DPC features in dynamically combining candidates of various lengths and outperforms both the straight-forward algorithm SPC and the fixed passes combined counting algorithm FPC. Extensive experimental results also show that all the three algorithms scale up linearly with respect to dataset sizes and cluster sizes.

A framework of sensor-cloud integration opportunities and challenges

Abstract: In the past few years, wireless sensor networks (WSNs) have been gaining increasing attention because of their potential of enabling of novel and attractive solutions in areas such as industrial automation, environmental monitoring, transportation business, health-care etc. If we add this collection of sensor derived data to various Web-based social networks or virtual communities, blogs etc., we can have a remarkable transformation in our ability to "see" ourselves and our planet. Our primary goal is to facilitate connecting sensors, people and software objects to build community-centric sensing applications. However, the computational tools needed to launch this exploration may be more appropriately built from the data center "Cloud" computing model than the traditional HPC approaches. In this paper, we propose a framework to enable this exploration by integrating sensor networks to the emerging data center "cloud" model of computing. But there are many challenges to enable this framework. We propose a pub-sub based model which simplifies the integration of sensor networks with cloud based community-centric applications. Also there is a need for internetworking cloud providers in case of violation of service level agreement with users. We discussed these issues and proposed reasonable solutions.

Cognitive radio network architecture: part I -- general structure

Abstract: Cognitive radio has been considered as a key technology for future wireless communications and mobile computing. We note the cognitive radios can form cognitive radio networks (CRN) by extending the radio link features to network layer functions and above. We categorize CRN architecture into several structures and classify the unidirectional links in such structures, to pave the way for future systematic CRN research.

Cooperative black and gray hole attacks in mobile ad hoc networks

Abstract: In this paper, we propose a complete protocol to detect a chain of cooperating malicious nodes in an ad hoc network that disrupts transmission of data by feeding wrong routing information. Our technique is based on sending data in equal but small sized blocks instead of sending whole of data in one continuous stream. The flow of traffic is monitored independently at the neighborhoods of both source and destination. The results of monitoring are gathered by a backbone network of trusted nodes. With assumption that a neighborhood of any node in the ad hoc network has more trusted nodes than malicious nodes, our protocol can not only detect but also remove a chain of cooperating malicious nodes (gray/black hole) by ensuring an end-to-end checking between the transmission of two blocks of data. The protocol takes O(mdBN) time for detection and removal of gray/black holes chain which betters an earlier O(n2) time bound [4] for detecting a single black hole in the network. Here, m is the number of malicious nodes in the network, dBN is the diameter of a backbone network formed out of the flat ad hoc network, and n is the total number of nodes in the ad hoc network.