| 1. |
- Corodescu, Andrei-Alin, et al.
(författare)
-
Big Data Workflows : Locality-Aware Orchestration Using Software Containers
- 2021
-
Ingår i: Sensors. - : MDPI AG. - 1424-8220. ; 21:24
-
Tidskriftsartikel (refereegranskat)abstract
- The emergence of the edge computing paradigm has shifted data processing from centralised infrastructures to heterogeneous and geographically distributed infrastructures. Therefore, data processing solutions must consider data locality to reduce the performance penalties from data transfers among remote data centres. Existing big data processing solutions provide limited support for handling data locality and are inefficient in processing small and frequent events specific to the edge environments. This article proposes a novel architecture and a proof-of-concept implementation for software container-centric big data workflow orchestration that puts data locality at the forefront. The proposed solution considers the available data locality information, leverages long-lived containers to execute workflow steps, and handles the interaction with different data sources through containers. We compare the proposed solution with Argo workflows and demonstrate a significant performance improvement in the execution speed for processing the same data units. Finally, we carry out experiments with the proposed solution under different configurations and analyze individual aspects affecting the performance of the overall solution.
|
|
| 2. |
- Corodescu, A. -A, et al.
(författare)
-
Locality-aware workflow orchestration for big data
- 2021
-
Ingår i: ACM International Conference Proceeding Series. - New York, NY, USA : Association for Computing Machinery. ; , s. 62-70
-
Konferensbidrag (refereegranskat)abstract
- The development of the Edge computing paradigm shifts data processing from centralised infrastructures to heterogeneous and geographically distributed infrastructure. Such a paradigm requires data processing solutions that consider data locality in order to reduce the performance penalties from data transfers between remote (in network terms) data centres. However, existing Big Data processing solutions have limited support for handling data locality and are inefficient in processing small and frequent events specific to Edge environments. This paper proposes a novel architecture and a proof-of-concept implementation for software container-centric Big Data workflow orchestration that puts data locality at the forefront. Our solution considers any available data locality information by default, leverages long-lived containers to execute workflow steps, and handles the interaction with different data sources through containers. We compare our system with Argo workflow and show significant performance improvements in terms of speed of execution for processing units of data using our data locality aware Big Data workflow approach.
|
|
| 3. |
- Dautaras, Justas, et al.
(författare)
-
Mobile Crowdsensing with Imagery Tasks
- 2021
-
Ingår i: Proceedings 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. - New York, NY, USA : Association for Computing Machinery (ACM). ; , s. 54-61
-
Konferensbidrag (refereegranskat)abstract
- The amount of gadgets connected to the internet has grown rapidly in the recent years. These human owned devices can potentially be used to gather sensor data without active involvement of their owners. One of the types of platforms that contribute to the utilisation of these devices are mobile crowdsensing systems. These systems can be used for different tasks including different types of community support. While these systems are quite widely used, yet little research has been done for integration of imagery data into them which require also human involvement. This paper considers a mobile crowdsensing system where gathering data from sensors is supported by crowdsourcing human intelligence for providing both textual and visual information. We also explore the best settings for such a system. Imagery processing is integrated into an already existing mobile crowdsensing platform CrowdS. The solution was evaluated both by a limited number of real life users and by conducting simulations. The simulations represent complex scenarios with multi-level variables. The results of simulation allow suggest an efficient configuration for the parameters and characteristics of the environment used in imagery integration.
|
|
| 4. |
- Dessalk, Yared Dejene, et al.
(författare)
-
Scalable Execution of Big Data Workflows using Software Containers
- 2020
-
Ingår i: Proceedings of the 12th International Conference on Management of Digital EcoSystems, MEDES 2020. - New York, NY, USA : Association for Computing Machinery, Inc. ; , s. 76-83
-
Konferensbidrag (refereegranskat)abstract
- Big Data processing involves handling large and complex data sets, incorporating different tools and frameworks as well as other processes that help organisations make sense of their data collected from various sources. This set of operations, referred to as Big Data workflows, require taking advantage of the elasticity of cloud infrastructures for scalability. In this paper, we present the design and prototype implementation of a Big Data workflow approach based on the use of software container technologies and message-oriented middleware (MOM) to enable highly scalable workflow execution. The approach is demonstrated in a use case together with a set of experiments that demonstrate the practical applicability of the proposed approach for the scalable execution of Big Data workflows. Furthermore, we present a scalability comparison of our proposed approach with that of Argo Workflows-one of the most prominent tools in the area of Big Data workflows.
|
|
| 5. |
- Dokoohaki, Nima, et al.
(författare)
-
Achieving Optimal Privacy in Trust-Aware Social Recommender Systems
- 2010
-
Ingår i: SOCIAL INFORMATICS. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 9783642165665 ; , s. 62-79
-
Konferensbidrag (refereegranskat)abstract
- Collaborative filtering (CF) recommenders are subject to numerous shortcomings such as centralized processing, vulnerability to shilling attacks, and most important of all privacy. To overcome these obstacles, researchers proposed for utilization of interpersonal trust between users, to alleviate many of these crucial shortcomings. Till now, attention has been mainly paid to strong points about trust-aware recommenders such as alleviating profile sparsity or calculation cost efficiency, while least attention has been paid on investigating the notion of privacy surrounding the disclosure of individual ratings and most importantly protection of trust computation across social networks forming the backbone of these systems. To contribute to addressing problem of privacy in trust-aware recommenders, within this paper, first we introduce a framework for enabling privacy-preserving trust-aware recommendation generation. While trust mechanism aims at elevating recommenders accuracy, to preserve privacy, accuracy of the system needs to be decreased. Since within this context, privacy and accuracy are conflicting goals we show that a Pareto set can be found as an optimal setting for both privacy-preserving and trust-enabling mechanisms. We show that this Pareto set, when used as the configuration for measuring the accuracy of base collaborative filtering engine, yields an optimized tradeoff between conflicting goals of privacy and accuracy. We prove this concept along with applicability of our framework by experimenting with accuracy and privacy factors, and we show through experiment how such optimal set can be inferred.
|
|
| 6. |
- Dokoohaki, Nima, et al.
(författare)
-
An Enterprise Social Recommendation System for Connecting Swedish Professionals
- 2014
-
Ingår i: Proceedings - IEEE 38th Annual International Computers, Software and Applications Conference Workshops, COMPSACW 2014. - : IEEE Communications Society. - 9781479935789 ; , s. 234-239
-
Konferensbidrag (refereegranskat)abstract
- Most cooperative businesses rely on some form of social networking system to facilitate user profiling and networking of their employees. To facilitate the discovery, matchmaking and networking among the co-workers across the enterprises social recommendation systems are often used. Off-the-shelf nature of these components often makes it hard for individuals to control their exposure as well as their preferences of whom to connect to. To this end, trust based recommenders have been amongst the most popular and demanding solutions due to their advantage of using social trust to generate more accurate suggestions for peers to connect to. They also allow individuals to control their exposure based on explicit trust levels. In this work we have proposed for an enterprise trust-based recommendation system with privacy controls. To generate accurate predictions, a local trust metric is defined between users based on correlations of user's profiled content such as blogging, articles wrote, comments, and likes along with profile information such as organization, region, interests or skills. Privacy metric is defined in such a way that users have full freedom either to hide their data from the recommender or customize their profiles to make them visible only to users with defined level of trustworthy.
|
|
| 7. |
|
|
| 8. |
- Dokoohaki, Nima, et al.
(författare)
-
Personalizing Human Interaction through Hybrid Ontological Profiling : Cultural Heritage Case Study
- 2008
-
Ingår i: 1st Workshop on Semantic Web Applications and Human Aspects, (SWAHA08). ; , s. 133-140
-
Konferensbidrag (refereegranskat)abstract
- In this paper we present a novel user profile formalization, which allows describingthe user attributes as well as history of user access for personalized, adaptive and interactiveexperience while we believe that our approach is applicable to different semantic applicationswe illustrate our solution in the context of online and onsite museums and exhibits visit. Weargue that a generic structure will allow incorporation of multiple dimensions of user attributesand characteristics as well as allowing different abstraction levels for profile formalization andpresentations. In order to construct such profile structures we extend and enrich existingmetadata vocabularies for cultural heritage to contain keywords pertaining to usage attributesand user related keywords. By extending metadata vocabularies we allow improvedmatchmaking between extended user profile contents and cultural heritage contents. Thisextension creates the possibility of further personalization of access to cultural heritageavailable through online and onsite digital libraries.
|
|
| 9. |
- Dokoohaki, Nima, et al.
(författare)
-
Quest : An Adaptive Framework for User Profile Acquisition from Social Communities of Interest
- 2010
-
Ingår i: Proceedings - 2010 International Conference on Advances in Social Network Analysis and Mining, ASONAM 2010. - 9780769541389 ; , s. 360-364
-
Konferensbidrag (refereegranskat)abstract
- Within this paper we introduce a framework for semi- to full-automatic discovery and acquisition of bag-of-words style interest profiles from openly accessible Social Web communities. To do such, we construct a semantic taxonomy search tree from target domain (domain towards which we're acquiring profiles for), starting with generic concepts at root down to specific-level instances at leaves, then we utilize one of proposed Quest methods, namely Depth-based, N-Split and Greedy to read the concept labels from the tree and crawl the source Social Network for profiles containing corresponding topics. Cached profiles are then mined in a two-step approach, using a clusterer and a classifier to generate predictive model presenting weighted profiles, which are used later on by a semantic recommender to suggest and recommend the community members with the items of their similar interest.
|
|
| 10. |
- Dokoohaki, Nima, et al.
(författare)
-
Structural Determination of Ontology-Driven Trust Networks in Semantic Social Institutions and Ecosystems
- 2007
-
Ingår i: Proceedings of the International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies (UBICOMM'07) and the International Conference on Advances in Semantic Processing SEMAPRO. - 0769529933 ; , s. 263-268
-
Konferensbidrag (refereegranskat)abstract
- Social institutions and ecosystems are growing across the web and social trust networks formed within these systems create an extraordinary test-bed to study relation dependant notions such as trust, reputation and belief. In order to capture, model and represent the semantics of trust relationships forming the trust networks, main components of relationships are represented and described using ontologies. This paper investigates how effective design of trust ontologies can improve the structure of trust networks created and implemented within semantic web-driven social institutions and systems. Based on the context of our research, we represent a trust ontology that captures the semantics of the structure of trust networks based on the context of social institutions and ecosystems on semantic web.
|
|
| 11. |
- Erliksson, Karl Fredrik, et al.
(författare)
-
Cross-Domain Transfer of Generative Explanations Using Text-to-Text Models
- 2021
-
Ingår i: Lecture Notes in Computer Science. - Cham : Springer Nature. ; , s. 76-89
-
Konferensbidrag (refereegranskat)abstract
- Deep learning models based on the Transformers architecture have achieved impressive state-of-the-art results and even surpassed human-level performance across various natural language processing tasks. However, these models remain opaque and hard to explain due to their vast complexity and size. This limits adoption in highly-regulated domains like medicine and finance, and often there is a lack of trust from non-expert end-users. In this paper, we show that by teaching a model to generate explanations alongside its predictions on a large annotated dataset, we can transfer this capability to a low-resource task in another domain. Our proposed three-step training procedure improves explanation quality by up to 7% and avoids sacrificing classification performance on the downstream task, while at the same time reducing the need for human annotations.
|
|
| 12. |
- Fazeli, Soude, et al.
(författare)
-
Elevating Prediction Accuracy in Trust-aware Collaborative Filtering Recommenders through T-index Metric and TopTrustee lists
- 2010
-
Ingår i: Journal of Emerging Technologies in Web Intelligence. - : Engineering and Technology Publishing. - 1798-0461. ; 2:4, s. 300-309
-
Tidskriftsartikel (refereegranskat)abstract
- The growing popularity of Social Networks raises the important issue of trust. Among many systems which have realized the impact of trust, Recommender Systems have been the most influential ones. Collaborative Filtering Recommenders take advantage of trust relations between users for generating more accurate predictions. In this paper, we propose a semantic recommendation framework for creating trust relationships among all types of users with respect to different types of items, which are accessed by unique URI across heterogeneous networks and environments. We gradually build up the trust relationships between users based on the rating information from user profiles and item profiles to generate trust networks of users. For analyzing the formation of trust networks, we employ Tindex as an estimate of a user’s trustworthiness to identify and select neighbors in an effective manner. In this work, we utilize T-index to form the list of an item’s raters, called TopTrustee list for keeping the most reliable users who have already shown interest in the respective item. Thus, when a user rates an item, he/she is able to find users who can be trustworthy neighbors even though they might not be accessible within an upper bound of traversal path length. An empirical evaluation demonstrates how T-index improves the Trust Network structure by generating connections to more trustworthy users. We also show that exploiting Tindex results in better prediction accuracy and coverage of recommendations collected along few edges that connect users on a Social Network.
|
|
| 13. |
- Fernando, Tharidu, et al.
(författare)
-
WorkflowDSL : Scalable Workflow Execution with Provenance for Data Analysis Applications
- 2018
-
Ingår i: Proceedings - International Computer Software and Applications Conference. - : IEEE Computer Society. - 9781538626665 ; , s. 774-779
-
Konferensbidrag (refereegranskat)abstract
- Data analysis projects typically use different programming languages (from Python for prototyping to C++ for support of runtime constraints) at their different stages by different experts. This creates a need for a data processing framework that is re-usable across multiple programming languages and supports collaboration of experts. In this work, we discuss implementation of a framework which uses a Domain Specific Language (DSL), called WorkflowDSL, that enables domain experts to collaborate on fine-tuning workflows. The framework includes support for parallel execution without any specialized code. It also provides a provenance capturing framework that enables users to analyse past executions and retrieve complete lineage of any data item generated. Graph database is used for storing provenance data. Advantages of usage of a graph database compare to relational databases are demonstrated. Experiments which were performed using a real-world scientific workflow from the bioinformatics domain and industrial data analysis models show that users were able to execute workflows efficiently when using WorkflowDSL for workflow composition and Python for task implementations. Moreover, we show that capturing provenance data can be useful for analysing past workflow executions.
|
|
| 14. |
- Hammar, Kim, et al.
(författare)
-
Deep text classification of Instagram data using word embeddings and weak supervision
- 2020
-
Ingår i: WEB INTELLIGENCE. - : IOS PRESS. - 2405-6456. ; 18:1, s. 53-67
-
Tidskriftsartikel (refereegranskat)abstract
- With the advent of social media, our online feeds increasingly consist of short, informal, and unstructured text. Instagram is one of the largest social media platforms, containing both text and images. However, most of the prior research on text processing in social media is focused on analyzing Twitter data, and little attention has been paid to text mining of Instagram data. Moreover, many text mining methods rely on training data annotated manually by humans, which in practice is both difficult and expensive to obtain. In this paper, we present methods for weakly supervised text classification of Instagram text. We analyze a corpora of Instagram posts from the fashion domain and train a deep clothing classifier with weak supervision to classify Instagram posts based on the associated text. With our experiments, we demonstrate that in absence of annotated training data, using weak supervision to train models is a viable approach. With weak supervision we were able to label a large dataset in hours, something that would have taken months to do with human annotators. Using the dataset labeled with weak supervision in combination with generative modeling, an F-1 score of 0.61 is achieved on the task of classifying the image contents of Instagram posts based solely on the associated text, which is on level with human performance.
|
|
| 15. |
- Hammar, Kim, et al.
(författare)
-
Deep Text Mining of Instagram Data Without Strong Supervision
- 2018
-
Ingår i: Proceedings - 2018 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2018. - : IEEE. - 9781538673256 ; , s. 158-165
-
Konferensbidrag (refereegranskat)abstract
- With the advent of social media, our online feeds increasingly consist of short, informal, and unstructured text. This textual data can be analyzed for the purpose of improving user recommendations and detecting trends. Instagram is one of the largest social media platforms, containing both text and images. However, most of the prior research on text processing in social media is focused on analyzing Twitter data, and little attention has been paid to text mining of Instagram data. Moreover, many text mining methods rely on annotated training data, which in practice is both difficult and expensive to obtain. In this paper, we present methods for unsupervised mining of fashion attributes from Instagram text, which can enable a new kind of user recommendation in the fashion domain. In this context, we analyze a corpora of Instagram posts from the fashion domain, introduce a system for extracting fashion attributes from Instagram, and train a deep clothing classifier with weak supervision to classify Instagram posts based on the associated text. With our experiments, we confirm that word embeddings are a useful asset for information extraction. Experimental results show that information extraction using word embeddings outperforms a baseline that uses Levenshtein distance. The results also show the benefit of combining weak supervision signals using generative models instead of majority voting. Using weak supervision and generative modeling, an F1 score of 0.61 is achieved on the task of classifying the image contents of Instagram posts based solely on the associated text, which is on level with human performance. Finally, our empirical study provides one of the few available studies on Instagram text and shows that the text is noisy, that the text distribution exhibits the long-tail phenomenon, and that comment sections on Instagram are multi-lingual.
|
|
| 16. |
- Haseeb, Abdul, et al.
(författare)
-
DeLP Based Semantic Location Lattice for Intelligent Robotic Navigation
- 2008
-
Ingår i: Proceedings of the 2008 International Conference on Artificial Intelligence, ICAI 2008 and Proceedings of the 2008 International Conference on Machine Learning; Models, Technologies and Applications. - 1601320701 - 9781601320728 ; , s. 686-692
-
Konferensbidrag (refereegranskat)abstract
- Location models require a well-defined representation of spatial connectivity and hierarchical relationship between different spatial concepts; and are fundamental for location navigation, location based services and contextual query responses. Current location models rely on a priori knowledge of surrounding environment and mostly the semantics of relationships are over-looked. In this paper we propose an incremental semantic spatial relationship building approach for robotic agents based on formal concept analysis and defeasible reasoning. We consider a number of cases in which an autonomous robot with incomplete information about the environment can perform reasoning and update its location navigation. We use contextual information for establishing strength of partial order relationship between discovered concepts of robotic navigation/computing environment.
|
|
| 17. |
|
|
| 18. |
- Haseeb, Abdul, et al.
(författare)
-
Distributed Discovery and Invocation of Web Services in Infrastructure-less Dynamic Environments
- 2009
-
Ingår i: International Journal of Web Services Practices (IJWSP). - 1738-6535. ; 3:3-4, s. 171-184
-
Tidskriftsartikel (refereegranskat)abstract
- Mobile autonomous systems like robot swarms or mobile software agents operate in a dynamic environment pertaining self-organization, selfconfiguration and heterogeneity of computing entities. In such settings there is a need for autonomic publishing and discovery of resources and just-in-time integration for on-the-fly service consumption without any a priori knowledge of available services both within the execution environment and from the outside world. We propose a mediator-based distributed Web services discovery and invocation middleware. Moreover we present experimental results on an implemented robot swarm simulation environment. We propose a conceptual classification of computing entities on the basis of communication capabilities and conceptual overlay formation for query propagation. Our approach provides a loose coupling in terms of space and time and uses both Internet-based communication and RDF-based communication via messages mediators/post-boxes between entities when inter-communication between entities is not possible.
|
|
| 19. |
- Haseeb, Abdul, et al.
(författare)
-
Light-Weight Decentralized Autonomic Web Service Discovery for Systems with Heterogeneous Communication Capabilities
- 2008
-
Ingår i: the proceedings of 12th IASTED International Conference on Internet and Multimedia Systems and Applications (IMSA.08). - 9780889867512 ; , s. 7-18
-
Konferensbidrag (refereegranskat)abstract
- Interoperability between autonomous systems like robot swarm or mobile software agents rely on efficient and seamless communication. Such mobile and dynamic environments pertain self-organization and self configuration of computing entities, a need for autonomic publishing and discovery of resources, and communication from and to outside world. Furthermore, such systems are attributed by heterogeneous communication capabilities of various computing entities. We take Web services approach for robot swarm based on robotic communication capabilities and propose a collaborative and decentralized services discovery and management middleware. Our approach provides a loose coupling in terms of space and time and uses both Internet based communication and RFID tags as message post boxes/relays for communication between robots when communication over the Internet is not available.
|
|
| 20. |
- Haseeb, Abdul, et al.
(författare)
-
Mediator-based Distributed Web Services Discovery and Invocation for Infrastructure-less Mobile Dynamic Systems
- 2008
-
Ingår i: proceedings of 4th International IEEE Conference of Next generation Web services practices (NWeSP.08). - 9780769534558 ; , s. 46-53
-
Konferensbidrag (refereegranskat)abstract
- Mobile autonomous systems like robot swarms or mobile software agents operate in a dynamic environment pertaining self-organization, self configurationand heterogeneity of computing entities.In such settings there is a need for autonomicpublishing and discovery of resources and just-in-timeintegration for on-the-fly service consumption withoutany a priori knowledge of available services both withinthe execution environment and from the outsideworld. We propose a mediator-based distributed Webservices discovery and invocation middleware.Moreover we present experimental results on animplemented robot swarm simulation environment. Wepropose a conceptual classification of computingentities on the basis of communication capabilities andconceptual overlay formation for query propagation.Our approach provides a loose coupling in terms ofspace and time and uses both Internet-basedcommunication and RDF-based communication viamessages mediators/post-boxes between entities wheninter-communication between entities is not possible.
|
|
| 21. |
- Haseeb, Abdul, et al.
(författare)
-
Semantic Middleware for Robot Swarm Interaction through Web Services
- 2008
-
Ingår i: MIC Special Session on Computing Systems in Dynamic Environments. - 9780889867116
-
Konferensbidrag (refereegranskat)abstract
- In this paper we propose a semantic middleware architecture and communication support for environments with swarm robots. Our main assumption is that robots can communicate via wireless networks while we don't assume high processing power in the robots. Basic advantage of the proposed middleware is the extension of robots' capabilities via access to semantic information and powerful processing engines. The architecture is conformant with main standard solutions and allows reusing intelligent functionality implemented in the external world.
|
|
| 22. |
- Heiberg, T., et al.
(författare)
-
An agent-based architecture for customer services management and product search
- 2002
-
Ingår i: Informatica (Vilnius). - 0868-4952 .- 1822-8844. ; 13:4, s. 441-454
-
Tidskriftsartikel (refereegranskat)abstract
- The amount of products and services available over the Internet increases significantly and it soon becomes beyond users ability to analyze and compare them. At the same time the number of potential customers available via the Internet also increases dramatically and starts to be beyond the service providers ability to perform efficient targeted marketing. A possible way for relaxing the above-mentioned limitations could be in usage of electronic assistants, both for customers and providers. Such assistants may serve as mediators for commercial Internet-based activity. Software agents could play role of such mediators representing customers and providers in the network. In this paper we present our experience and a solution to using agent technology in customer services management for mobile users. The solution is intended to increase granularity and personalization in targeted advertising while ensuring customer privacy. The proposed solution has been implemented in a prototype system for providing services for,users of mobile devices.
|
|
| 23. |
|
|
| 24. |
- Jaradat, Shatha, et al.
(författare)
-
Dynamic CNN Models For Fashion Recommendation in Instagram
- 2018
-
Ingår i: 2018 IEEE INT CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, UBIQUITOUS COMPUTING & COMMUNICATIONS, BIG DATA & CLOUD COMPUTING, SOCIAL COMPUTING & NETWORKING, SUSTAINABLE COMPUTING & COMMUNICATIONS. - : IEEE COMPUTER SOC. - 9781728111414 ; , s. 1144-1151
-
Konferensbidrag (refereegranskat)abstract
- Instagram as an online photo-sharing and social-networking service is becoming more powerful in enabling fashion brands to ramp up their business growth. Nowadays, a single post by a fashion influencer attracts a wealth of attention and a magnitude of followers who are curious to know more about the brands and style of each clothing item sitting inside the image. To this end, the development of efficient Deep CNN models that can accurately detect styles and brands have become a research challenge. In addition, current techniques need to cope with inherent fashion-related data issues. Namely, clothing details inside a single image only cover a small proportion of the large and hierarchical space of possible brands and clothing item attributes. In order to cope with these challenges, one can argue that neural classifiers should become adapted to large-scale and hierarchical fashion datasets. As a remedy, we propose two novel techniques to incorporate the valuable social media textual content to support the visual classification in a dynamic way. The first method is adaptive neural pruning (DynamicPruning) in which the clothing item category detected from posts' text analysis can be used to activate the possible range of connections of clothing attributes' classifier. The second method (DynamicLayers) is a dynamic framework in which multiple-attributes classification layers exist and a suitable attributes' classifier layer is activated dynamically based upon the mined text from the image. Extensive experiments on a dataset gathered from Instagram and a baseline fashion dataset (DeepFashion) have demonstrated that our approaches can improve the accuracy by about 20% when compared to base architectures. It is worth highlighting that with Dynamiclayers we have gained 35% accuracy for the task of multi-class multi-labeled classification compared to the other model.
|
|
| 25. |
- Jaradat, Shatha, et al.
(författare)
-
Learning What to Share in Online Social Networks Using Deep Reinforcement Learning
- 2018
-
Ingår i: Machine Learning Techniques for Online Social Networks. - Cham : Springer International Publishing. ; , s. 115-133
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- Online networking sites tried their best to have right privacy mechanisms in place for users, enabling them to share the right content with the right audience. With all these efforts, privacy customizations remain hard for users across the sites. Existing research that addresses this problem mainly focuses on semi-supervised strategies that introduce extra complexity by requiring the user to manually specify initial privacy preferences for their friends. In this work, we suggest a deep reinforcement learning framework that can dynamically generate privacy labels for users in OSNs. We evaluated our framework on a 1 year crawl of Twitter data, using different types of recurrent units in recurrent neural networks (RNN): Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Simple RNN. Our experiments revealed that LSTM performed better than GRU in terms of top users detection accuracy and the ranked dependence between the generated privacy labels and estimated user trust values.
|
|
| 26. |
- Jaradat, Shatha
(författare)
-
Mining of User Profiles in Online Social Networks for Improved Personalized Recommendations
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- We have focused on influencer-based marketing in online social networks as a source of implicit learning about the preferences of social media users. Those users who use social networks on a daily basis are also the online shoppers who are confronted with huge information overload and a wide variety of online products and brands to choose from. The role of digital influencers in promoting products and spreading information to a large scale of followers who engage with the influencers’ posts and interact with them is our key to better understanding of these followers’ tastes and future purchase intentions. Hence, the analysis and the extraction of fine-grained details (which we refer to as user profiling) from digital influencers media content serves in collecting more information about the implicit preferences of their followers. With this knowledge, the chances of offering social media users better personalized services are enhanced. In this thesis, we empower cross-domain recommendations through the development of novel methods and algorithms for improving personalization through the effective mining of user profiles in online social networks. We developed a semantic information extraction framework from social media textual content that is able to capture fine-grained attributes with respect to the defined online shops taxonomy. Results form the aforementioned framework have been applied as input to the approaches we proposed to incorporate extracted textual hints in supporting the visual fine-grained classification of social media images in a dynamic way. Our methods have improved the classification accuracy when compared to state-of-the-art approaches. Moreover, we suggested solutions for incorporating the extracted products’ meta-data in embedding-based personalized recommendation architectures where our strategies improved the recommendations’ quality. In order to speed up the process of preparing large scale social media images datasets for deep learning image analysis, we developed a complete framework for detailed annotation, object localization and semantic segmentation. As our focus is also directed towards the analysis of interactions between social media users, we proposed a neural reinforcement learning approach that is based on estimating the established trust levels between social media users for controlling the amount of recommended updates they get from each other. Moreover, we proposed enhanced topic modelling algorithm for supporting interpretable yet dynamic summarizations of large social media contents.
|
|
| 27. |
- Jaradat, Shatha, et al.
(författare)
-
Outfit2Vec : Incorporating Clothing Hierarchical MetaData into Outfits’ Recommendation
- 2020
-
Ingår i: Fashion Recommender Systems. - : Springer International Publishing. ; , s. 87-107
-
Bokkapitel (refereegranskat)abstract
- Fashion Personalisation is emerging as a major service that online retailers and brands are competing to provide. They aim to deliver more tailored recommendations to increase revenues and satisfy customers by providing them options of similar items according to their purchase history. However, many online retailers still struggle with turning customers’ data into actionable and intelligent recommendations that reflect their personalised and preferred taste of style. On the other hand due to the ever increasing use of social media, fashion brands invest in influencers’ marketing to advertise their brands to reach a larger segment of customers who strongly trust their influencers’ choices. In this context the textual and visual analysis of social media can be used to extract semantic knowledge about customers’ preferences that can be further applied in generating tailored online shopping recommendations. As style lies in the details of outfits, recommendation models should leverage the fashion metadata ranging from clothing categories and subcategories to attributes such as materials and patterns to overall style description in order to generate fine-grained recommendations. Recently, several recommendation algorithms suggested to model the latent representations of items and users with neural word embeddings approaches which showed improved results. Inspired by Paragraph Vector neural embeddings model, we present Outfit2vec and PartialOutfit2vec in which we leverage the complex relationship between user’s fashion metadata while generating outfits’ embeddings. In this paper, we also describe a methodology to generate representative vectors of hierarchically-composed fashion outfits. We evaluate our models using different strategies in comparison to the paragraph embedding models on an extensively-annotated Instagram dataset on recommendation and multi-class style classification tasks. Our models achieve better results specially in whole outfits’ ranking evaluations with an average of 22% increase.
|
|
| 28. |
|
|
| 29. |
- Jaradat, Shatha, et al.
(författare)
-
TALS : A framework for text analysis, fine-grained annotation, localisation and semantic segmentation
- 2019
-
Ingår i: Proceedings - International Computer Software and Applications Conference. - : IEEE Computer Society. - 9781728126074 ; , s. 201-206
-
Konferensbidrag (refereegranskat)abstract
- With around 2.77 billion users using online social media platforms nowadays, it is becoming more attractive for business retailers to reach and to connect to more potential clients through social media. However, providing more effective recommendations to grab clients’ attention requires a deep understanding of users’ interests. Given the enormous amounts of text and images that users share in social media, deep learning approaches play a major role in performing semantic analysis of text and images. Moreover, object localisation and pixel-by-pixel semantic segmentation image analysis neural architectures provide an enhanced level of information. However, to train such architectures in an end-to-end manner, detailed datasets with specific meta-data are required. In our paper, we present a complete framework that can be used to tag images in a hierarchical fashion, and to perform object localisation and semantic segmentation. In addition to this, we show the value of using neural word embeddings in providing additional semantic details to annotators to guide them in annotating images in the system. Our framework is designed to be a fully functional solution capable of providing fine-grained annotations, essential localisation and segmentation services while keeping the core architecture simple and extensible. We also provide a fine-grained labelled fashion dataset that can be a rich source for research purposes.
|
|
| 30. |
- Khan, Akif Quddus, et al.
(författare)
-
A Taxonomy for Cloud Storage Cost
- 2024
-
Ingår i: Management of Digital EcoSystems - 15th International Conference, MEDES 2023, Revised Selected Papers. - : Springer Nature. ; , s. 317-330
-
Konferensbidrag (refereegranskat)abstract
- The cost of using cloud storage services is complex and often an unclear structure, while it is one of the important factors for organisations adopting cloud storage. Furthermore, organisations take advantage of multi-cloud or hybrid solutions to combine multiple public and/or private cloud service providers to avoid vendor lock-in, achieve high availability and performance, optimise cost, etc. This complicated ecosystem makes it even harder to understand and manage cost. Therefore, in this paper, we provide a taxonomy of cloud storage cost in order to provide a better understanding and insights on this complex problem domain.
|
|
| 31. |
- Khan, Akif Quddus, et al.
(författare)
-
Cloud storage cost: a taxonomy and survey
- 2024
-
Ingår i: World wide web (Bussum). - : Springer. - 1386-145X .- 1573-1413. ; 27:4
-
Tidskriftsartikel (refereegranskat)abstract
- Cloud service providers offer application providers with virtually infinite storage and computing resources, while providing cost-efficiency and various other quality of service (QoS) properties through a storage-as-a-service (StaaS) approach. Organizations also use multi-cloud or hybrid solutions by combining multiple public and/or private cloud service providers to avoid vendor lock-in, achieve high availability and performance, and optimise cost. Indeed cost is one of the important factors for organizations while adopting cloud storage; however, cloud storage providers offer complex pricing policies, including the actual storage cost and the cost related to additional services (e.g., network usage cost). In this article, we provide a detailed taxonomy of cloud storage cost and a taxonomy of other QoS elements, such as network performance, availability, and reliability. We also discuss various cost trade-offs, including storage and computation, storage and cache, and storage and network. Finally, we provide a cost comparison across different storage providers under different contexts and a set of user scenarios to demonstrate the complexity of cost structure and discuss existing literature for cloud storage selection and cost optimization. We aim that the work presented in this article will provide decision-makers and researchers focusing on cloud storage selection for data placement, cost modelling, and cost optimization with a better understanding and insights regarding the elements contributing to the storage cost and this complex problem domain.
|
|
| 32. |
- Khan, Akif Quddus, et al.
(författare)
-
Smart Data Placement for Big Data Pipelines : An Approach based on the Storage-as-a-Service Model
- 2022
-
Ingår i: 2022 IEEE/ACM 15TH INTERNATIONAL CONFERENCE ON UTILITY AND CLOUD COMPUTING, UCC. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 317-320
-
Konferensbidrag (refereegranskat)abstract
- The development of big data pipelines is a challenging task, especially when data storage is considered as part of the data pipelines. Local storage is expensive, hard to maintain, comes with several challenges (e.g., data availability, data security, and backup). The use of cloud storage, i.e., Storageas-a-Service (StaaS), instead of local storage has the potential of providing more flexibility in terms of such as scalability, fault tolerance, and availability. In this paper, we propose a generic approach to integrate StaaS with data pipelines, i.e., computation on an on-premise server or on a specific cloud, but integration with StaaS, and develop a ranking method for available storage options based on five key parameters: cost, proximity, network performance, the impact of server-side encryption, and user weights. The evaluation carried out demonstrates the effectiveness of the proposed approach in terms of data transfer performance and the feasibility of dynamic selection of a storage option based on four primary user scenarios.
|
|
| 33. |
- Khan, Akif Quddus, et al.
(författare)
-
Smart Data Placement Using Storage-as-a-Service Model for Big Data Pipelines
- 2023
-
Ingår i: Sensors. - : MDPI AG. - 1424-8220. ; 23:2
-
Tidskriftsartikel (refereegranskat)abstract
- Big data pipelines are developed to process data characterized by one or more of the three big data features, commonly known as the three Vs (volume, velocity, and variety), through a series of steps (e.g., extract, transform, and move), making the ground work for the use of advanced analytics and ML/AI techniques. Computing continuum (i.e., cloud/fog/edge) allows access to virtually infinite amount of resources, where data pipelines could be executed at scale; however, the implementation of data pipelines on the continuum is a complex task that needs to take computing resources, data transmission channels, triggers, data transfer methods, integration of message queues, etc., into account. The task becomes even more challenging when data storage is considered as part of the data pipelines. Local storage is expensive, hard to maintain, and comes with several challenges (e.g., data availability, data security, and backup). The use of cloud storage, i.e., storage-as-a-service (StaaS), instead of local storage has the potential of providing more flexibility in terms of scalability, fault tolerance, and availability. In this article, we propose a generic approach to integrate StaaS with data pipelines, i.e., computation on an on-premise server or on a specific cloud, but integration with StaaS, and develop a ranking method for available storage options based on five key parameters: cost, proximity, network performance, server-side encryption, and user weights/preferences. The evaluation carried out demonstrates the effectiveness of the proposed approach in terms of data transfer performance, utility of the individual parameters, and feasibility of dynamic selection of a storage option based on four primary user scenarios.
|
|
| 34. |
- Khan, Akif Quddus, et al.
(författare)
-
Towards Cloud Storage Tier Optimization with Rule-Based Classification
- 2023
-
Ingår i: Service-Oriented and Cloud Computing. - : Springer Nature. ; , s. 205-216
-
Konferensbidrag (refereegranskat)abstract
- Cloud storage adoption has increased over the years as more and more data has been produced with particularly high demand for fast processing and low latency. To meet the users’ demands and to provide a cost-effective solution, cloud service providers (CSPs) have offered tiered storage; however, keeping the data in one tier is not a cost-effective approach. Hence, several two-tiered approaches have been developed to classify storage objects into the most suitable tier. In this respect, this paper explores a rule-based classification approach to optimize cloud storage cost by migrating data between different storage tiers. Instead of two, four distinct storage tiers are considered, including premium, hot, cold, and archive. The viability and potential of the approach are demonstrated by comparing cost savings achieved when data was moved between tiers versus when it remained static. The results indicate that the proposed approach has the potential to significantly reduce cloud storage cost, thereby providing valuable insights for organizations seeking to optimize their cloud storage strategies. Finally, the limitations of the proposed approach are discussed along with the potential directions for future work, particularly the use of game theory to incorporate a feedback loop to extend and improve the proposed approach accordingly.
|
|
| 35. |
- Khan, Akif Quddus, et al.
(författare)
-
Towards Graph-based Cloud Cost Modelling and Optimisation
- 2023
-
Ingår i: Proceedings. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1337-1342
-
Konferensbidrag (refereegranskat)abstract
- Cloud computing has become an increasingly popular choice for businesses and individuals due to its flexibility, scalability, and convenience; however, the rising cost of cloud resources has become a significant concern for many. The pay-per-use model used in cloud computing means that costs can accumulate quickly, and the lack of visibility and control can result in unexpected expenses. The cost structure becomes even more complicated when dealing with hybrid or multi-cloud environments. For businesses, the cost of cloud computing can be a significant portion of their IT budget, and any savings can lead to better financial stability and competitiveness. In this respect, it is essential to manage cloud costs effectively. This requires a deep understanding of current resource utilization, forecasting future needs, and optimising resource utilization to control costs. To address this challenge, new tools and techniques are being developed to provide more visibility and control over cloud computing costs. In this respect, this paper explores a graph-based solution for modelling cost elements and cloud resources and potential ways to solve the resulting constraint problem of cost optimisation. We primarily consider utilization, cost, performance, and availability in this context. Such an approach will eventually help organizations make informed decisions about cloud resource placement and manage the costs of software applications and data workflows deployed in single, hybrid, or multi-cloud environments.
|
|
| 36. |
- Khan, Basit, et al.
(författare)
-
A Platform for Actively Supporting e-Learning in Mobile Networks
- 2010
-
Ingår i: International Journal of Mobile and Blended Learning. - : IGI Global. - 1941-8647 .- 1941-8655. ; 2, s. 55-79
-
Tidskriftsartikel (refereegranskat)abstract
- The ubiquitous availability of wireless networks has opened new possibilities for individuals to learn from each other in open learning spaces like cities. Therefore, the changed learning environment must be understood by e-learning systems and technological facilities must be provided for knowledge sharing and construction. Such systems need to be pedagogically sound, yet adaptive to altered modalities. The teacher who was once the central entity to fulfill the learner’s needs may not always be available. Therefore, e-learning systems would fill the gap created by this teacher unavailability by actively participating in learning activities and performing some of the teacher’s roles. This article proposes an architecture designed to meet such challenges in a city-wide context. The authors outline the main components and services needed to fulfill the new requirements and provide the learners with tools, services and educational support for learning activities.
|
|
| 37. |
|
|
| 38. |
|
|
| 39. |
- Khan, Basit, et al.
(författare)
-
Multiagent system to support Place/Space based mobile learning in city
- 2011
-
Ingår i: International Conference on Information Society, i-Society 2011. - : IEEE. - 9780956426383 ; , s. 66-71
-
Konferensbidrag (refereegranskat)abstract
- Different approaches have been developed to provide technical support for mobile learning. Most these approaches consider only the physical properties of learning environment. In this work, we not only focus on the physical/spatial dimension of the learning environment of the city, but also pay attention to the notion of Place which is a meaningful outcome of peoples understanding of Space. This paper illustrates how a theoretical conceptualization of Spaces and Places is mapped into a multiagent framework called AGORA. It presents the design aspects of a mobile learning system, which uses software agents as its core functional units. We discuss how the theoretical concepts are used to define a technical solution to support mobile learning in a citywide context.
|
|
| 40. |
- Khan, Basit, et al.
(författare)
-
Towards a Places and Spaces based city-wide mobile learning through multi-agent support
- 2011
-
Ingår i: Digital Ecosystems and Technologies Conference (DEST), 2011 Proceedings of the 5th IEEE International Conference on. - : IEEE. - 9781457708725 - 9781457708718 ; , s. 164-169
-
Konferensbidrag (refereegranskat)abstract
- This paper illustrates how the conceptualization of Places can be used to inform the technical design of mobile learning system. We apply the concept of Place in a multi-agent framework for supporting informal city-wide mobile learning activities. By taking input from the theoretical framework for analysing collaborative learning activities, we adopt the structure and organization of multi-gent framework. The functionality and components of the system are defined in light of the theoretical work. This work bridges the gap between theory and it's application in technology for mobile learning in our project.
|
|
| 41. |
|
|
| 42. |
- Kungas, Peep, et al.
(författare)
-
Analyzing Web Services Networks : Theory and Practice
- 2014
-
Ingår i: Advanced Web Services. - New York : Springer-Verlag New York. - 9781461475347 - 9781461475354 ; , s. 381-406
-
Bokkapitel (refereegranskat)abstract
- This paper addresses the problem of applying the general network theory for analyzing qualitatively Web services networks. The paper reviews current approaches to analyzing Web services networks, generalizes the published approaches into a formal framework for analyzing Web services networks and demonstrates its applicability in practice. More specifically, two case studies are described where the presented framework has been applied. The first one considers identification of redundant data in large-scale service-oriented information systems, while the second one measures information diffusion between individual information systems.
|
|
| 43. |
- Kungas, Peep, et al.
(författare)
-
Combining Symbolic and Non-Symbolic Negotiation for Agent-Based Web Service Composition
- 2005
-
Ingår i: Proceedings of the 2005 International Conference on Artificial Intelligence ICAI'05. - : CSREA Press. ; , s. 513-519
-
Konferensbidrag (refereegranskat)abstract
- The paper presents an architecture and a methodology for agent-based Web service discovery and composition. We assume that Web services are described in DAML-S. Since DAML-S represents declarative information about services, symbolic reasoning can be applied for search or composition of new services automatically. We propose the usage of symbolic agent negotiation for dynamic Web service discovery and composition, while nonsymbolic negotiation is applied for negotiating over the cost or other attributes of the composite service. Therefore, by using symbolic negotiation for automated service composition, we support declarative information gathering and integration during service composition, whilst non-symbolic negotiation facilitates pragmatic issues of Web service execution.
|
|
| 44. |
|
|
| 45. |
- Kungas, Peep, et al.
(författare)
-
Detection of Missing Web Services: The Partial Deduction Approach
- 2005
-
Ingår i: Proceedings of International Conference on Next Generation Web Services Practices, NWeSP'05. - : IEEE Computer Society. ; , s. 339-344
-
Konferensbidrag (refereegranskat)abstract
- Many methods have been recently proposed for composing automatically Web services from existing ones. The methods range from AI planning to automated theorem proving and graph search algorithms. However the usability of these methods is greatly affected by two assumptions. Firstly, it is assumed that developers provide consistent declarative descriptions of Web services. Secondly, it is assumed that there exists a sufficient set of atomic Web services, which would facilitate the composition of all other Web services. In this paper we propose a method to ensure these two assumptions by using analysis of Web services' descriptions. In particular we apply partial deduction for identifying possible inconsistencies in Web service descriptions. Our method also determines possibly missing atomic Web services, which should be implemented in order to compose a requested composite Web service.
|
|
| 46. |
- Kungas, Peep, et al.
(författare)
-
From web services annotation and composition to web services domain analysis
- 2007
-
Ingår i: International Journal of Metadata, Semantics and Ontologies. - 1744-2621 .- 1744-263X. ; 2:3, s. 157-178
-
Tidskriftsartikel (refereegranskat)abstract
- Automated web service annotation and composition are seen as complimentary technologies. While automated annotation allows to extract web service semantics from existing WSDL documents, automated composition uses this semantics for integrating applications. Anyway, automated composition can be applied not only to constructing new but also to analysis of existent web services. Therefore applicability of both methodologies is essential for increasing the productivity of information system integration. In this paper we propose application of automated composition for analysing web services domains. We identify and analyse some general web services properties in the context of industrial and public web services.
|
|
| 47. |
- Kungas, Peep, et al.
(författare)
-
Interaction and Potential Synergy between Commercial and Governmental Web Services : a Case Study
- 2007
-
Ingår i: SERVICES 2007, Proceedings of 2007 IEEE Congress on Services. - 0769529267 - 0769529267 ; , s. 1-8
-
Konferensbidrag (refereegranskat)abstract
- Recent progress in the field of Web services has resulted in deployment of a significant number of Web services. Furthermore, it is expected that the number of available Web services will constantly grow in the following years. Due to the high number of available Web services, it is a hard task for developers and business analysts to choose which Web services are most suitable for integration. However, despite the increased academic and commercial interest to Web services, there is currently no survey available analysing most relevant Web services. Moreover, to the best of our knowledge, there is no publicly available study analysing the structure and potential synergy between commercial and governmental Web services. In this paper we target these shortcomings by providing a case study of automated Web service composition for semantically annotated commercial and governmental Web services. We propose a method for identifying most applicable Web services and demonstrate it on a case study. We also analyse interaction and potential synergy between commercial and governmental Web services.
|
|
| 48. |
- Kungas, Peep, et al.
(författare)
-
Linear logic, partial deduction and cooperative problem solving
- 2004
-
Ingår i: Lecture Notes in Computer Science. - BERLIN : SPRINGER. - 0302-9743 .- 1611-3349. ; 2990, s. 263-279
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper we present a model of cooperative problem solving (CPS). Linear Logic (LL) is used for encoding agents' states, goals and capabilities. LL theorem proving is applied by each agent to determine whether the particular agent is capable of solving the problem alone. If no individual solution can be constructed, then the agent may start negotiation with other agents in order to find a cooperative solution. Partial deduction in LL is used to derive a possible deal. Finally proofs are generated and plans are extracted from the proofs. The extracted plans determine agents' responsibilities in cooperative solutions.
|
|
| 49. |
- Kungas, Peep, et al.
(författare)
-
Partial Deduction for assisting Automated Semantic Web Service Composition
- 2005
-
Ingår i: Proceedings of the Workshop on Exploring Planning and Scheduling for Web Services, Grid and Autonomic Computing held in conjunction with The Twentieth National Conference on Artificial Intelligence , (AAAI 2005). ; , s. 43-45
-
Konferensbidrag (refereegranskat)
|
|
| 50. |
- Kungas, Peep, et al.
(författare)
-
Partial deduction for linear logic - The symbolic negotiation perspective
- 2005
-
Ingår i: Agents and Peer-To-Peer Computing. - BERLIN : SPRINGER. - 3540261729 ; , s. 35-52
-
Konferensbidrag (refereegranskat)abstract
- Symbolic negotiation is regarded in the field of computer science as a process, where parties try to reach an agreement on the high-level means for achieving their goals by applying symbolic reasoning techniques. It has been proposed [1] that symbolic negotiation could be formalised as Partial Deduction (PD) in Linear Logic (LL). However, the paper [1] did not provided a formalisation of the PD process in LL. In this paper we fill the gap by providing a formalisation of PD for !-Horn fragment of LL. The framework can be easily extended for other fragments of LL as well such that more comprehensive aspects of negotiation can be described. In this paper we consider also soundness and completeness of the formalism. It turns out that, given a certain PD procedure, PD for LL in !-Horn fragment is sound and complete. We adopt the hypothesis that an essential component of symbolic negotiation is Cooperative Problem Solving (CPS). Thus a formal system for symbolic negotiation would consist of CPS rules plus negotiationspecific rules. In this paper only CPS rules are under investigation while negotiation-specific rules shall be published in another paper.
|
|
