Hybrid Recommender System for Movies Using Device Information

Farman Ullah,Ghulam Sarwar,Kim Jae Woo(김재우),Park Yun Kyung(박윤경),Moon Kyeong Deok(문경덕),Lee Sung Chang(이성창) 한국통신학회 2012 한국통신학회 학술대회논문집 Vol.2012 No.2

A Network and Visual Quality Aware N-Screen Content Recommender System Using Joint Matrix Factorization

Ullah, Farman,Sarwar, Ghulam,Lee, Sungchang Hindawi Publishing Corporation 2014 The Scientific World Journal Vol.2014 No.-

<P>We propose a network and visual quality aware N-Screen content recommender system. N-Screen provides more ways than ever before to access multimedia content through multiple devices and heterogeneous access networks. The heterogeneity of devices and access networks present new questions of QoS (quality of service) in the realm of user experience with content. We propose, a recommender system that ensures a better visual quality on user's N-screen devices and the efficient utilization of available access network bandwidth with user preferences. The proposed system estimates the available bandwidth and visual quality on users N-Screen devices and integrates it with users preferences and contents genre information to personalize his N-Screen content. The objective is to recommend content that the user's N-Screen device and access network are capable of displaying and streaming with the user preferences that have not been supported in existing systems. Furthermore, we suggest a joint matrix factorization approach to jointly factorize the users rating matrix with the users N-Screen device similarity and program genres similarity. Finally, the experimental results show that we also enhance the prediction and recommendation accuracy, sparsity, and cold start issues.</P>

Identification of influential nodes based on temporal-aware modeling of multi-hop neighbor interactions for influence spread maximization

Ullah, Farman,Lee, Sungchang Elsevier 2017 PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIO Vol.486 No.-

<P><B>Abstract</B></P> <P>This paper presents the identification of highly influential nodes based on temporal-aware modeling of multi-hop neighbor interactions to maximize the spread of information in online social networks (OSNs). The objective is to choose a set of influential nodes that have higher temporal multi-hop interactions and more topological connections in large-scale OSNs to maximize information dissemination and minimize spreading time. An influence diffusion process that is solely based on topology is not able to capture the influence spreading efficiently. A temporal multi-hops social interaction based centrality is proposed to choose nodes of higher spreading ability considering the nodes’ neighbors and neighbors-of-neighbors temporal modeled interactions and topological connections. The temporal-aware interactions are modeled to find users who are more active recently. First, we model the influence between users considering the temporal interactions of the user and its neighbors. A subset of nodes with a higher influence value and more topological connections with direct neighbors is selected. Secondly, we select the Top- K higher influential spreader nodes from the subset of nodes considering the node neighbors and neighbors-of-neighbors temporal modeled social interactions and topological connections. Finally, the proposed algorithm is evaluated using the epidemic spreading models. The experimental results show that the algorithm is able to extract highly influential nodes that maximize the spread of information and minimize contagion time.</P> <P><B>Highlights</B></P> <P> <UL> <LI> We proposed temporal-aware modeling of multi-hop interaction based centrality measure to identify highly influential nodes. </LI> <LI> We considered the nodes’ neighbors and neighbors-of-neighbors temporal modeled interactions and topological connection for ranking the nodes. </LI> <LI> The proposed method has better performance of identifying the influential node that can maximize the information spread and minimize the spreading time. </LI> <LI> The results are verified on three real publically available dataset and compared it with seven existing algorithms. </LI> </UL> </P>

Growth and Simultaneous Valleys Manipulation of Two-Dimensional MoSe₂-WSe₂ Lateral Heterostructure

Ullah, Farman,Sim, Yumin,Le, Chinh Tam,Seong, Maeng-Je,Jang, Joon I.,Rhim, Sonny H.,Tran Khac, Bien Cuong,Chung, Koo-Hyun,Park, Kibog,Lee, Yangjin,Kim, Kwanpyo,Jeong, Hu Young,Kim, Yong Soo American Chemical Society 2017 ACS NANO Vol.11 No.9

<P>The covalently bonded in-plane heterostructure (HS) of monolayer transition-metal dichalcogenides (TMDCs) possesses huge potential for high-speed electronic devices in terms of valleytronics. In this study, high-quality monolayer MoSe2WSe2 lateral HSs are grown by pulsed-laser-deposition-assisted selenization method. The sharp interface of the lateral HS is verified by morphological and optical characterizations. Intriguingly, photoluminescence spectra acquired from the interface show rather clear signatures of pristine MoSe2 and WSe2 with no intermediate energy peak related to intralayer excitonic matter or formation of MoxW(1-x)Se2 alloys, thereby confirming the sharp interface. Furthermore, the discrete nature of laterally attached TMDC monolayers, each with doubly degenerated but nonequivalent energy valleys marked by (K-M, K'(M)) for MoSe2, and (K-w, K'(w)) for WSe2 in k space, allows simultaneous control of the four valleys within the excitation area without any crosstalk effect over the interface. As an example, K-M and K-w valleys or K'(M) and K'(w) valleys are simultaneously polarized by controlling the helicity of circularly polarized optical pumping, where the maximum degree of polarization is achieved at their respective band edges. The current work provides the growth mechanism of laterally sharp HSs and highlights their potential use in valleytronics.</P>

Molecular Epidemiology of Methicillin Resistant Staphylococcus aureus Colonization in Burnt Patients

Farman Ullah Khan,Bashir Ahmad,Jawad Ahmed,Sun Young Hwang,Han Sang Yoo 대한수의학회 2013 대한수의학회 학술대회발표집 Vol.2013 No.-

Community clustering based on trust modeling weighted by user interests in online social networks

Ullah, Farman,Lee, Sungchang Elsevier 2017 Chaos, solitons, and fractals Vol.103 No.-

<P><B>Abstract</B></P> <P>Online social networking websites provide platforms through which users can express opinions and preferences on a multitude of items and topics, and follow users and information, and flood it by retweeting. User-user interests vary, and based on the users’ interests, they can be grouped to multiple implicit interest communities. However, every interaction and user may not be trustworthy. Capturing the user's interaction with others, and predicting user interest and trust from the interactions are important parts of social media analytics. In this paper, we propose community clustering for implicit community detection based on trust and interest modeling. The trust modeling is weighted by the user's interests to group the users in multiple clusters having higher interest and trust similarity within a cluster. The proposed community clustering algorithm begins by ranking the nodes by the weighted degree and then selecting the initial community centers that are not in the neighbors of each other's. We then assign the user to the community with whom the user has the higher interest and trust similarity and higher common connections topology. We provide a probabilistic trust model to predict the unknown reliable trust between users considering their friends. We model user interests based on preferences and opinions, as well as the content experienced in social media. Furthermore, we evaluate the proposed algorithm comparing publicly available datasets with well-known algorithms for clustering quality.</P>

시간 정보를 이용한 확장성 있는 하이브리드 Recommender 시스템

Farman Ullah,Ghulam Sarwar,김재우,문경덕,김진태,이성창 한국인터넷방송통신학회 2012 한국인터넷방송통신학회 논문지 Vol.12 No.2

최근 디지털 컨텐츠와 컨텐츠 사용자의 기하 급수적인 증가와 함께 recommender 시스템이 주목을 받으며 많은 응용 프로그램에 적용되고 있는 가운데, recommender 시스템의 확장성과 대체적으로 이와 반비례하는 정확성이 이슈가 되고 있다. 본 논문에서는 recommender 시스템 모델 중 하이브리드 모델의 매트릭스를 제거하고 아이템의 특성을 정하기 위해 클러스터링 기술을 사용한 Scalable Hybrid Recommender System을 제안한다. 제안된 모델은 recommender 시스템의 확장성과 정확성을 향상시키기 위해서 아이템에 대한 사용자의 평가 정보, demographic 정보와 구체적인 시간 정보를 사용한다. Reduction 기술 사용을 통해 Item-feature 매트릭스의 사이즈를 축소하고, 사용자 demographic 정보를 사용하여 temporal aware hybrid user model을 만든 후, 비슷한 정보를 가진 사용자간 클러스터링을 통해, 가장 유사한 정보를 가진 사용자들을 추출하여, 사용자간 정보를 비교함으로써 사용자가 원하는 아이템의 특성을 예상하고 사용자에게 N개의 아이템을 추천함으로써, 기존의 recommender 시스템보다 더욱 향상된 결과를 도출해 낼 수 있는 알고리즘을 제시하였다. Recommender Systems have gained much popularity among researchers and is applied in a number of applications. The exponential growth of users and products poses some key challenges for recommender systems. Recommender Systems mostly suffer from scalability and accuracy. The accuracy of Recommender system is somehow inversely proportional to its scalability. In this paper we proposed a Context Aware Hybrid Recommender System using matrix reduction for Hybrid model and clustering technique for predication of item features. In our approach we used user item-feature rating, User Demographic information and context information i.e. specific time and day to improve scalability and accuracy. Our Algorithm produce better results because we reduce the dimension of items features matrix by using different reduction techniques and use user demographic information, construct context aware hybrid user model, cluster the similar user offline, find the nearest neighbors, predict the item features and recommend the Top N- items.

Morphological Studies of the Predatory Ladybird Beetle Stethorus vegans (Blackburn) (Coleoptera: Coccinellidae)

Farman Ullah,Inamullah Khan,Hart, Robert-Spooner,Peter Bailey,Khalil, Said-Khan Korean Society of Applied Entomology 2002 Journal of Asia-Pacific Entomology Vol.5 No.1

Morphological features of the ladybird beetle Stethorus vegans (Blackburn) were studied at 25 $\pm$ $2^{\circ}$ with a photoperiod of 16L: 8D. All stages of S. vahans were examined under a stereo-zoom microscope. Newly laid eggs were translucent white, turning pale yellow after 4-5 hours. The mean egg dimension was 0.36 x 0.19 mm. Eggs laid by unmated females did not hatch or show any signs of development. Newly emerged larvae were white in color, but soon became pale creamy-white. There were four larval instars, which were differentiated from each other by the presence of exuviae and differences in head capsule size. The pre-pupa, not a distinct stage in the life cycle but a quiescent period at the end of the 4th larval instar, lasted for several hours. Pupae were oval, flattened and black-brown with (me hair like setae on their dorsal sides with a mean length and width of 1.06 x 0.74 mm. The adults were oval, convex and black with small yellow setae on their dorsal side.

Effects of Maillard reaction on physicochemical and functional properties of walnut protein isolate

Sahibzada Fahim Ullah,Nasir Mehmood Khan,Farman Ali,Shujaat Ahmad,Zia Ullah Khan,Noor Rehman,Abdul Khaliq Jan,Nawshad Muhammad 한국식품과학회 2019 Food Science and Biotechnology Vol.28 No.5

In this study, the Maillard reaction (MR) ofglucose was applied to improve the physicochemical andfunctional properties of walnut protein isolate (WNPI). TheMR products (MRPs) were prepared with glucose at 0 h(MRP0), 1 h (MRP1), 2 h (MRP2) and 3 h (MRP3) heatingat 95 C. The Infra-Red spectrum showed reduction ofamide and S–H functionalities in MRPs with completeintermixing of glucose in MRP3. Scanning electronmicroscopy indicated changes in the morphology of MRP3which also exhibited promising antioxidant effect. Significantdecrease (P\0.05) in hydrophobicity values (Ho)and increase (P\0.05) in emulsifying activity/emulsifyingstability indexes values were observed for MRPs. Uniform droplet distribution was observed in microscopyof emulsions while an increase in the interfacial proteinconcentration (U) was obtained for MRPs. These resultssuggest that MR is useful in improving the utilization ofthis protein in food product development.

UAV-enabled healthcare architecture: Issues and challenges

Ullah, Sana,Kim, Ki-Il,Kim, Kyong Hoon,Imran, Muhammad,Khan, Pervez,Tovar, Eduardo,Ali, Farman North-Holland 2019 Future generations computer systems Vol.97 No.-

<P><B>Abstract</B></P> <P>Unmanned Aerial Vehicles (UAVs) have great potential to revolutionize the future of automotive, energy, and healthcare sectors by working as wireless relays to improve connectivity with ground networks. They are able to collect and process real-time information by connecting existing network infrastructures including Internet of Medical Things (e.g., Body Area Networks (BANs)) and Internet of Vehicles with clouds or remote servers. In this article, we advocate and promote the notion of employing UAVs as data collectors. To demonstrate practicality of the idea, we propose a UAV-based architecture to communicate with BANs in a reliable and power-efficient manner. The proposed architecture adopts the concept of wakeup-radio based communication between a UAV and multiple BANs. We analyze the performance of the proposed protocol in terms of throughput and delay by allocating different priorities to the hubs or gateways. The proposed architecture may be useful in remote or disaster areas, where BANs have poor or no access to conventional wireless communication infrastructure, and may even assist vehicular networks by monitoring driver’s physiological conditions through BANs. We further highlight open research issues and challenges that are important for developing efficient protocols for UAV-based data collection in smart healthcare systems.</P>