Zeitschriftenartikel
  • B. Mbarek
  • Mouzhi Ge
  • T. Pitner
Trust-Based Authentication for Smart Home Systems, vol. 117, pg. 2157-2172.
  • 2021

DOI: 10.1007/s11277-020-07965-0

Smart home systems are developed to interconnect and automate household appliances and create ubiquitous home services. Such a system is mainly driven by the communications among Internet-of-Things (IoT) objects along with Radio Frequency IDentification (RFID) technologies, where the RFID techniques in the IoT network are commonly prone to malicious attacks due to the inherent weaknesses of underlying wireless radio communications. Thus, it causes the smart home systems vulnerable to some active attacks such as the jamming and cloning attacks, which in turn threaten to home breach and personal information disclosure. This paper therefore proposes a new trust-based authentication scheme to effectively address two typical attacks, jamming and cloning attacks, in smart home environment. The evaluation shows that our solution can significantly reduce the authentication failure in jamming attacks, increase the detection probability of cloning attacks, and improve the authentication efficiency to manage the authentication delay in a reasonable time.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • B. Mbarek
  • Mouzhi Ge
  • T. Pitner
Trust-based Detection Strategy against Replication Attacks in IoT, pg. 1–12.
  • 2021
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
A Hybrid Data-driven Model for Intrusion Detection in VANET, vol. 184, pg. 516-523.
  • 2021

DOI: 10.1016/j.procs.2021.03.065

Nowadays, VANET (Vehicular Ad-hoc NETwork) has gained increasing attention from many researchers with its various applications, such as enhancing traffic safety by collecting and disseminating traffic event information. This increased interest in VANET has necessitated greater scrutiny of machine learning (ML) methods used for improving the security capabilities of intrusion detection systems (IDSs), such as the need to solve computationally intensive ML problems due to the increased vehicular data. Therefore, in this paper, we propose a hybrid ML model to enhance the performance of IDSs by dealing with the explosive growth in computing power and the need for detecting malicious incidents timely. The proposed approach mainly uses the advantages of Random Forest to detect known network intrusions. Besides, there is a post-detection phase to detect possible novel intruders by using the advantages of coresets and clustering algorithms. Our approach is evaluated over a very recent IDS dataset named CICIDS2017. The preliminary results show that the proposed hybrid model can increase the utility of IDSs.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • J. Blanco
  • Mouzhi Ge
  • T. Pitner
Modeling Inconsistent Data for Reasoners in Web of Things[Accepted for publication], pg. 1-9.
  • 2021
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • A. Tóth
  • Mouzhi Ge
A Deployable Data as a Service Architecture for Enterprises, pg. 1-8.
  • 2021
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
  • L. Trang
Towards faster big data analytics for anti‐jamming applications in vehicular ad‐hoc network, pg. 1-22.
  • 2021

DOI: 10.1002/ett.4280

Nowadays, Wireless Vehicular Ad-Hoc Network (VANET) has become a valuable asset for transportation systems. However, this advanced technology is characterized by highly distributed and networked environment, which makes VANET communications vulnerable to malicious jamming attacks. Although Big Data Analytics has been used to solve this critical security issue by supporting the development of anti-jamming applications, as the amount of vehicular data is growing exponentially, the anti-jamming applications face many challenges (i., reactions in real-time) due to the lack of specific solutions that can keep up with the fast advancement of VANET. In this paper, we propose a new vehicular data prioritization model based on coresets to accelerate the Big Data Analytics in VANET. Our experimental evaluation shows that our solution can significantly increase the efficiency for clustering in jamming detection while keeping and improving the clustering quality. Also, the proposed solution can enable the real-time detection and be integrated to anti-jamming applications.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Q. Yang
  • Mouzhi Ge
  • M. Helfert
Developing Reliable Taxonomic Features for Data Warehouse Architectures, pg. 241-249.
  • 2020

DOI: 10.1109/CBI49978.2020.00033

Since there is a large variety of data warehouse architectures with different structures and components, it is very difficult and time-consuming to systematically analyse them and obtain insights from those architectures. One effective way to understand those architectures is using a taxonomy to classify them. However, most of the taxonomic features are derived in an ad-hoc way and the reliability of those features is unknown. This paper therefore is to develop a set of reliable features by modeling different data warehouse architectures and further generate the structural knowledge represented by a taxonomy. This taxonomy is further validated by evaluating two real-world data warehouse architectures from IBM and Facebook.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • F. Persia
  • D. DAuria
  • Mouzhi Ge
Improving Learning System Performance with Multimedia Semantics, pg. 238-241.
  • 2020

DOI: 10.1109/ICSC.2020.00050

Nowadays, different new learning methodologies have been proposed to achieve effective learning in University education. One of the most promising methodologies for teaching computer science is multimedia-based education. In order to empower the performance within the online learning platforms, such as Moodle or OLE, this paper proposes to integrate the multimedia-based education to learning systems, and conducts an experiment with the operating system course. We show that exploiting multimedia, such as educational video and smart text, can significantly improve the student's learning performance in terms of exam grade and knowledge transfer. Further, the paper presents a real-world case study depicting how to enhance the performance of learning platform with multimedia semantics.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • Mouzhi Ge
  • W. Lewoniewski
Developing the Quality Model for Collaborative Open Data, vol. 176, pg. 1883-1892.
  • 2020

DOI: 10.1016/j.procs.2020.09.228

Nowadays, the development of data sharing technologies allows to involve more people to collaboratively contribute knowledge on the Web. The shared knowledge is usually represented as Collaborative Open Data (COD), for example, Wikipedia is one of the well-known sources for COD. The Wikipedia articles can be written in different languages, updated in real time, and originated from a vast variety of editors. However, COD also bring different data quality problems such as data inconsistency and low data objectiveness due to the crowd-based and dynamic nature. These data quality problems such as biased information may lead to sentimental changes or social impacts. This paper therefore proposes a new measurement model to assess the quality of COD. In order to evaluate the proposed model, A preliminary experiment is conducted with a large scale of Wikipedia articles to validate the applicability and efficiency of this proposed quality model in the real-world scenario.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • B. Mbarek
  • Mouzhi Ge
  • T. Pitner
An Efficient Mutual Authentication Scheme for Internet of Things, vol. 9, pg. 100160.
  • 2020

DOI: 10.1016/j.iot.2020.100160

The Internet of Things (IoT) is developed to facilitate the connections and data sharing among people, devices, and systems. Among the infrastructural IoT techniques, Radio Frequency IDentification (RFID) has been used to enable the proliferation and communication in IoT networks. However, the RFID techniques usually suffer from security issues due to the inherent weaknesses of underlying wireless radio communications. One of the main security issues is the authentication vulnerability from the jamming attack. In order to tackle the vulnerabilities of key updating algorithms, this paper therefore proposes an efficient authentication scheme based on the self-adaptive and mutual key updating. Furthermore, we evaluate the performance and applicability of our solution with a thorough simulation by taking into account the energy consumption, authentication failure rate and authentication delay. The feasibility and applicability are demonstrated by implementing the proposed authentication scheme in smart home IoT systems.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • F. Persia
  • G. Pilato
  • Mouzhi Ge
  • P. Bolzoni
  • D. D’Auria
  • S. Helmer
Improving orienteering-based tourist trip planning with social sensing, vol. 110, pg. 931-945.
  • 2020

DOI: 10.1016/j.future.2019.10.028

We enhance a tourist trip planning framework based on orienteering with category constraints by adding social sensing. This allows us to customize a user’s experience without putting the burden of preference elicitation on the user. We identify the interests of a user by analyzing their Tweets and then match these interests to descriptions of points of interests. For this analysis we adapt different schemes for social sensing to the needs of our orienteering context and compare them to find the most suitable approach. We show that our technique is fast enough for use in real-time dynamic settings and also has a higher accuracy compared to previous approaches. Additionally, we integrate a more efficient algorithm for solving the orienteering problem, boosting the overall performance and utility of our framework further, as demonstrated by the positive user satisfaction received by real users.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • M. Elahi
  • N. El Ioini
  • A. Alexander Lambrix
  • Mouzhi Ge
Exploring Personalized University Ranking and Recommendation, pg. 6-10.
  • 2020

DOI: 10.1145/3386392.3397590

Finding the right university to study is still a challenge for many people due to the large number of universities worldwide. Although there exist a number of global university rankings, they provide non# personalized rankings as one-size-fits-all solution. This becomes an issue since different people may have different preferences and considerations in mind, when choosing the university to study. This paper addresses this problem and presents a Recommender System to generate a personalized ranking list based on users particular preferences. The system is capable of eliciting users preferences, provided as ratings for universities, building predictive models on the preference data, and generating a personalized university ranking list that is tailored to the particular preferences and needs of the users. We performed two sets of experiments. First, we conducted an offline experiment using a dataset of user preferences, collected by the early version of our system. This allowed us to cross-validate and compare different recommender algorithms and choose the most accurate recommender algorithm that can better suit the particular problem at hand. We integrated the chosen algorithm in the final implementation of our system. As the follow-up, we performed a user study in order to analyze whether or not the final version of our system is usable from the perception of users. The results showed that the system has scored well above the benchmark and users assessed it as "good" in term of usability.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • M. Macak
  • Mouzhi Ge
  • B. Buhnova
A Cross-Domain Comparative Study of Big Data Architectures, vol. 29, pg. 2030001.
  • 2020

DOI: 10.1142/S0218843020300016

Nowadays, a variety of Big Data architectures are emerging to organize the Big Data life cycle. While some of these architectures are proposed for general usage, many of them are proposed in a specific application domain such as smart cities, transportation, healthcare, and agriculture. There is, however, a lack of understanding of how and why Big Data architectures vary in different domains and how the Big Data architecture strategy in one domain may possibly advance other domains. Therefore, this paper surveys and compares the Big Data architectures in different application domains. It also chooses a representative architecture of each researched application domain to indicate which Big Data architecture from a given domain the researchers and practitioners may possibly start from. Next, a pairwise cross-domain comparison among the Big Data architectures is presented to outline the similarities and differences between the domain-specific architectures. Finally, the paper provides a set of practical guidelines for Big Data researchers and practitioners to build and improve Big Data architectures based on the knowledge gathered in this study.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
Improving Big Data Clustering for Jamming Detection in Smart Mobility
  • 2020
Smart mobility, with its urban transportation services ranging from real-time traffic control to cooperative vehicle infrastructure systems, is becoming increasingly critical in smart cities. These smart mobility services thus need to be very well protected against a variety of security threats, such as intrusion, jamming, and Sybil attacks. One of the frequently cited attacks in smart mobility is the jamming attack. In order to detect the jamming attacks, different anti-jamming applications have been developed to reduce the impact of malicious jamming attacks. One important step in anti-jamming detection is to cluster the vehicular data. However, it is usually very time-consuming to detect the jamming attacks that may affect the safety of roads and vehicle communication in real-time. Therefore, this paper proposes an efficient big data clustering model, coresets-based clustering, to support the real-time detection of jamming attacks. We validate the model efficiency and applicability in the context of a typical smart mobility system: Vehicular Ad-hoc Network, known as VANET.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • M. Drăgoicea
  • L. Walletzký
  • L. Carrubbo
  • Nabil Badr
  • Angeliki T.
  • F. Romanovská
  • Mouzhi Ge
Service Design for Resilience: A Multi-Contextual Modeling Perspective, vol. 8, pg. 185526-185543.
  • 2020

DOI: 10.1109/ACCESS.2020.3029320

This paper introduces a conceptual framework aiming to broaden the discussion on resilience for the design of public services. From a theoretical point of view, the paper explores service design with a Systems Thinking lens. A multi-contextual perspective aiming to analyze, decompose, and design smart cities services where resilience is an input at the service design level is described and the four diamondsof-context model for service design (4DocMod) is introduced. This service model accommodates various actors' contexts in public service design and consists of four design artefacts, the diamonds (See, Recognize, Organize, Do). From a practical point of view, guidelines for the application of the 4DocMod service model extension for resilience are described along with two case studies addressing the recent COVID-19 pandemic that illustrates a clear situation of resilience with insights in multiple contexts. According to the findings of this paper, it is obvious that resilience is not “just”a request. Instead, it plays a higher role within the service system. It is not “just”another Context, either. Instead, it goes through many contexts with different circumstances. In this manner, it is possible to address the qualities through which actors can become resilient, at the service design stage, to ensure continuity of the public services in times of emergency. As our approach using the 4DocMod is proposing, resilience may be is achieved when specific properties are provisioned at information service design level.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • B. Mbarek
  • Mouzhi Ge
  • T. Pitner
Enhanced network intrusion detection system protocol for internet of things, pg. 1156-1163.
  • 2020
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • L. Walletzký
  • F. Romanovská
  • A. Toli
  • Mouzhi Ge
Research Challenges of Open Data as a Service for Smart Cities, pg. 468-472.
  • 2020
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • B. Mbarek
  • Mouzhi Ge
  • T. Pitner
Blockchain-Based Access Control for IoT in Smart Home Systems, pg. 17-32.
  • 2020
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • B. Mbarek
  • Mouzhi Ge
  • T. Pitner
Self-adaptive RFID Authentication for Internet of Things, pg. 1094-1105.
  • 2019
With the development of wireless Internet of Things (IoT) devices, Radio frequency identification (RFID) has been used as a promising technology for the proliferation and communication in IoT networks. However, the RFID techniques are usually plagued with security and privacy issues due to the inherent weaknesses of underlying wireless radio communications. Although several RFID authentication mechanisms have been proposed to address the security concerns in RFID, most of them are still vulnerable to some active attacks, especially the jamming attack. This paper therefore proposes a novel self-adaptive authentication mechanism with a robust key updating, in order to tackle the security vulnerabilities of key updating algorithms and their inability to jamming attacks. Furthermore, we assess the performance and applicability of our solution with a thorough simulation by taking into account the energy consumption and authentication failure rate.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • T. Chondrogiannis
  • Mouzhi Ge
Inferring ratings for custom trips from rich GPS traces, pg. 1-4.
  • 2019

DOI: 10.1145/3356994.3365502

Trip planning services are employed extensively by users to compute paths between locations and navigate within a road network. In some real-world scenarios such as planning for a hiking trip or running training, users usually require personalized trip planning. Although some existing systems can recommend trips that other users have posted, along with a set of ratings w.r.t. the difficulty of the route, conditions, or the enjoyment it provides. Very often though users want to define a custom trip that fits their personal needs, for which existing systems are unable to provide any rating. In this paper we therefore define the problem of inferring ratings for custom trips. We also outline a solution to infer ratings by utilizing the ratings of trips previously posted by users and their similarity with a given custom trip. Finally, we present the results of preliminary experiments were we evaluate the efficiency of our proposed approach on inferring ratings for trips related to hiking and other similar activities.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • D. DAuria
  • Mouzhi Ge
  • F. Persia
Exploiting Recommender Systems in Collaborative Healthcare, pg. 71-82.
  • 2019
With the development of new medical auxiliaries such as virtual reality and surgery robotics, recommender systems are emerged to interact with the medical auxiliaries and support doctor’s decisions and operations, especially in collaborative healthcare, recommender systems can interactively take into account the preferences and concerns from both patients and doctors. However, how to apply and integrate recommender systems is still not clear in collaborative healthcare. Therefore, from practical perspective this paper investigates the application of recommender systems in three typical collaborative healthcare domains, which are augmented/virtual reality, medicine and surgery robotics. The results not only provide the insights of how to integrate recommender systems with healthcare auxiliaries but also discuss the practical guidance of how to design recommender systems in collaborative healthcare.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
Quality Management for Big 3D Data Analytics: A Case Study of Protein Data Bank, pg. 286-293.
  • 2019

DOI: 10.5220/0007717402860293

3D data have been widely used to represent complex data objects in different domains such as virtual reality, 3D printing or biological data analytics. Due to complexity of 3D data, it is usually featured as big 3D data. One of the typical big 3D data is the protein data, which can be used to visualize the protein structure in a 3D style. However, the 3D data also bring various data quality problems, which may cause the delay, inaccurate analysis results, even fatal errors for the critical decision making. Therefore, this paper proposes a novel big 3D data process model with specific consideration of 3D data quality. In order to validate this model, we conduct a case study for cleaning and analyzing the protein data. Our case study includes a comprehensive taxonomy of data quality problems for the 3D protein data and demonstrates the utility of our proposed model. Furthermore, this work can guide the researchers and domain experts such as biologists to manage the quality of their 3D protein data.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • F. Persia
Factoring Personalization in Social Media Recommendations, pg. 344-347.
  • 2019
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • T. Chondrogiannis
  • Mouzhi Ge
Inferring ratings for custom trips from rich GPS traces, pg. 4:1-4:4.
  • 2019

DOI: 10.1145/3356994.3365502

Trip planning services are employed extensively by users to compute paths between locations and navigate within a road network. In some real-world scenarios such as planning for a hiking trip or running training, users usually require personalized trip planning. Although some existing systems can recommend trips that other users have posted, along with a set of ratings w.r.t. the difficulty of the route, conditions, or the enjoyment it provides. Very often though users want to define a custom trip that fits their personal needs, for which existing systems are unable to provide any rating. In this paper we therefore define the problem of inferring ratings for custom trips. We also outline a solution to infer ratings by utilizing the ratings of trips previously posted by users and their similarity with a given custom trip. Finally, we present the results of preliminary experiments were we evaluate the efficiency of our proposed approach on inferring ratings for trips related to hiking and other similar activities.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • L. Walletzky
  • L. Carubbo
  • Mouzhi Ge
Modelling Service Design and Complexity for Multi-contextual Applications in Smart Cities, pg. 101-106.
  • 2019

DOI: 10.1109/ICSTCC.2019.8885800

The paper aims to model and analyse the way how complex services can be designed. The main issue of the complex service design is that stakeholders act within different contexts, because most cases are with more than one value proposition chains of services. The design of such complex services cannot be in isolation from other services in the entire service ecosystem. Therefore, this paper proposes a model to show how the service can be decomposed to atomic elements and how they can be used to design service with a better value proposition for service receivers. One of the most important roles in service modelling is the agent, which can be the provider, collaborator, or receiver of the service. The way how individual agents and teams are organized in the value proposition chain is a key factor for increasing service efficiency. Thus, the agents are usually distributed in different teams, serving for different services in different contexts. However, all those actions can be related, and mostly the relations are affecting the behaviour of agents in different environments. The paper is therefore to address how to describe the role of each agent in a specific context and connect it with the other contexts in service design. In order to validate the model, this paper demonstrates how to model the services in the smart mobility applications
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
Quality Management for Big 3D Data Analytics: A Case Study of Protein Data Bank, pg. 286-293.
  • 2019

DOI: 10.5220/0007717402860293

3D data have been widely used to represent complex data objects in different domains such as virtual reality, 3D printing or biological data analytics. Due to complexity of 3D data, it is usually featured as big 3D data. One of the typical big 3D data is the protein data, which can be used to visualize the protein structure in a 3D style. However, the 3D data also bring various data quality problems, which may cause the delay, inaccurate analysis results, even fatal errors for the critical decision making. Therefore, this paper proposes a novel big 3D data process model with specific consideration of 3D data quality. In order to validate this model, we conduct a case study for cleaning and analyzing the protein data. Our case study includes a comprehensive taxonomy of data quality problems for the 3D protein data and demonstrates the utility of our proposed model. Furthermore, this work can guide the researchers and domain experts such as biologists to manage the quality of their 3D protein data.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
A Research Roadmap of Big Data Clustering Algorithms for Future Internet of Things, vol. 9, pg. 16-30.
  • 2019

DOI: 10.4018/IJOCI.2019040102

Due to the massive data increase in different Internet of Things (IoT) domains such as healthcare IoT and Smart City IoT, Big Data technologies have been emerged as critical analytics tools for analyzing the IoT data. Among the Big Data technologies, data clustering is one of the essential approaches to process the IoT data. However, how to select a suitable clustering algorithm for IoT data is still unclear. Furthermore, since Big Data technology are still in its initial stage for different IoT domains, it is thus valuable to propose and structure the research challenges between Big Data and IoT. Therefore, this article starts by reviewing and comparing the data clustering algorithms that can be applied in IoT datasets, and then extends the discussions to a broader IoT context such as IoT dynamics and IoT mobile networks. Finally, this article identifies a set of research challenges that harvest a research roadmap for the Big Data research in IoT domains. The proposed research roadmap aims at bridging the research gaps between Big Data and various IoT contexts.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • S. Chren
  • B. Rossi
  • B. Buhnova
  • Mouzhi Ge
  • T. Pitner
Industrial Involvement in Information System Education: Lessons Learned from a Software Quality Course
  • 2019
As Information System (IS) development is closely related to industry and real-world applications, industrial involvement is a critical element in IS education. This paper studies one typical IS course - a Software Quality course, and reflects our experience with involving a mix of industrial experts in building a practical IS course that would increase students’ competences in critical thinking about the consequences of the design and quality engineering decisions that they are making during software development. In the course design, the industrial experts are involved in lecturing, hands-on-exercise seminars and final student evaluation. We find that students are showing active course participation with our designed industrial involvement. Furthermore, we summarize lessons learned from the industry involvement, as well as the reflections on the value perceived by the industrial experts involved in the IS education.
  • Europan Campus Rottal-Inn
  • Angewandte Naturwissenschaften und Wirtschaftsingenieurwesen
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • L. Trang
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
Scaling Big Data Applications in Smart City with Coresets, pg. 357-363.
  • 2019

DOI: 10.5220/0007958803570363

With the development of Big Data applications in Smart Cities, various Big Data applications are proposed within the domain. These are however hard to test and prototype, since such prototyping requires big computing resources. In order to save the effort in building Big Data prototypes for Smart Cities, this paper proposes an enhanced sampling technique to obtain a coreset from Big Data while keeping the features of the Big Data, such as clustering structure and distribution density. In the proposed sampling method, for a given dataset and an ε>0, the method computes an ε-coreset of the dataset. The ε-coreset is then modified to obtain a sample set while ensuring the separation and balance in the set. Furthermore, by considering the representativeness of each sample point, our method can helps to remove noises and outliers. We believe that the coreset-based technique can be used to efficiently prototype and evaluate Big Data applications in the Smart City.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • S. Chren
  • B. Rossi
  • T. Pitner
Data Quality Management Framework for Smart Grid Systems, pg. 299-310.
  • 2019

DOI: 10.1007/978-3-030-20482-2_24

  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Q. Yang
  • Mouzhi Ge
  • M. Helfert
Analysis of Data Warehouse Architectures: Modeling and Classification, pg. 604-611.
  • 2019

DOI: 10.5220/0007728006040611

With decades of development and innovation, data warehouses and their architectures have been extended to a variety of derivatives in various environments to achieve different organisations’ requirements. Although there are some ad-hoc studies on data warehouse architecture (DWHA) investigations and classifications, limited research is relevant to systematically model and classify DWHAs. Especially in the big data era, data is generated explosively. More emerging architectures and technologies are leveraged to manipulate and manage big data in this domain. It is therefore valuable to revisit and investigate DWHAs with new innovations. In this paper, we collect 116 publications and model 73 disparate DWHAs using Archimate, then 9 representative DWHAs are identified and summarised into a”big picture”. Furthermore, it proposes a new classification model sticking to state-of-the-art DWHAs. This model can guide researchers and practitioners to identify, analyse and compare differences and trends of DWHAs from componental and architectural perspectives.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • Mouzhi Ge
  • V. Dohnal
Quality Management in Big Data, vol. 5, pg. 19.
  • 2018

DOI: 10.3390/informatics5020019

Due to the importance of quality issues in Big Data, Big Data quality management has attracted significant research attention on how to measure, improve and manage the quality for Big Data. This special issue in the Journal of Informatics thus tends to address the quality problems in Big Data as well as promote further research for Big Data quality. Our editorial describes the state-of-the-art research challenges in the Big Data quality research, and highlights the contributions of each paper accepted in this special issue.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Q. Yang
  • Mouzhi Ge
  • M. Helfert
Guildelines of Data Quality Issues for Data Integration in the Context of the TPC-DI Benchmark, pg. 135-144.
  • 2018
Nowadays, many business intelligence or master data management initiatives are based on regular data integration, since data integration intends to extract and combine a variety of data sources, it is thus considered as a prerequisite for data analytics and management. More recently, TPC-DI is proposed as an industry benchmark for data integration. It is designed to benchmark the data integration and serve as a standardisation to evaluate the ETL performance. There are a variety of data quality problems such as multi-meaning attributes and inconsistent data schemas in source data, which will not only cause problems for the data integration process but also affect further data mining or data analytics. This paper has summarised typical data quality problems in the data integration and adapted the traditional data quality dimensions to classify those data quality problems. We found that data completeness, timeliness and consistency are critical for data quality management in data integr ation, and data consistency should be further defined in the pragmatic level. In order to prevent typical data quality problems and proactively manage data quality in ETL, we proposed a set of practical guidelines for researchers and practitioners to conduct data quality management in data integration.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • Mouzhi Ge
  • H. Bangui
  • B. Buhnova
Big Data for Internet of Things: A Survey, vol. 87, pg. 601-614.
  • 2018

DOI: 10.1016/j.future.2018.04.053

With the rapid development of the Internet of Things (IoT), Big Data technologies have emerged as a critical data analytics tool to bring the knowledge within IoT infrastructures to better meet the purpose of the IoT systems and support critical decision making. Although the topic of Big Data analytics itself is extensively researched, the disparity between IoT domains (such as healthcare, energy, transportation and others) has isolated the evolution of Big Data approaches in each IoT domain. Thus, the mutual understanding across IoT domains can possibly advance the evolution of Big Data research in IoT. In this work, we therefore conduct a survey on Big Data technologies in different IoT domains to facilitate and stimulate knowledge sharing across the IoT domains. Based on our review, this paper discusses the similarities and differences among Big Data technologies used in different IoT domains, suggests how certain Big Data technology used in one IoT domain can be re-used in another IoT domain, and develops a conceptual framework to outline the critical Big Data technologies across all the reviewed IoT domains.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • Mouzhi Ge
  • F. Persia
A Generalized Evaluation Framework for Multimedia Recommender Systems, vol. 12, pg. 541-557.
  • 2018

DOI: 10.1142/S1793351X18500046

With the widespread availability of media technologies, such as real-time streaming, new Internet-of-Thing devices and smart phones, multimedia data are extensively increased and the big multimedia data rapidly spread over various social networks. This has created complexity and information overload for users to choose the suitable multimedia objects. Thus, different multimedia recommender systems have been emerging to help users find the useful multimedia objects that are possibly preferred by the user. However, the evaluation of these multimedia recommender systems is still in an ad-hoc stage. Given the distinct features of multimedia objects, the evaluation criteria adopted from the general recommender systems might not be effectively used to evaluate multimedia recommendations. In this paper, we therefore review and analyze the evaluation criteria that have been used in the previous multimedia recommender system papers. Based on the review, we propose a generalized evaluation framework to guide the researchers and practitioners to perform evaluations, especially user-centric evaluations, for multimedia recommender systems.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • F. Persia
  • Mouzhi Ge
  • D. DAuria
How to Exploit Recommender Systems in Social Media, pg. 537-541.
  • 2018

DOI: 10.1109/IRI.2018.00085

The rapid increase and widespread of social media data have created new research challenges and opportunities for social media recommender systems, which are designed to recommend personalized, interesting, credible social media content with possible social impact. However, due to complexity in social network and new media interaction, the research of social media recommender systems is still on its initial stage. Therefore, this paper aims to review the state-of-theart research that are related to social media recommender systems, and identify the critical factors for building new social media recommender systems. Our results show that relevance, validity, popularity, credibility and social impact are considered to be the 5 important factors for social media recommender systems.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Q. Yang
  • Mouzhi Ge
  • M. Helfert
Data Quality Problems in TPC-DI Based Data Integration Processes, pg. 57-73.
  • 2018
Many data driven organisations need to integrate data from multiple, distributed and heterogeneous resources for advanced data analysis. A data integration system is an essential component to collect data into a data warehouse or other data analytics systems. There are various alternatives of data integration systems which are created in-house or provided by vendors. Hence, it is necessary for an organisation to compare and benchmark them when choosing a suitable one to meet its requirements. Recently, the TPC-DI is proposed as the first industrial benchmark for evaluating data integration systems. When using this benchmark, we find some typical data quality problems in the TPC-DI data source such as multi-meaning attributes and inconsistent data schemas, which could delay or even fail the data integration process. This paper explains processes of this benchmark and summarises typical data quality problems identified in the TPC-DI data source. Furthermore, in order to prevent data quality problems and proactively manage data quality, we propose a set of practical guidelines for researchers and practitioners to conduct data quality management when using the TPC-DI benchmark.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
Exploring Big Data Clustering Algorithms for Internet of Things Applications, pg. 269-276.
  • 2018

DOI: 10.5220/0006773402690276

With the rapid development of the Big Data and Internet of Things (IoT), Big Data technologies have emerged as a key data analytics tool in IoT, in which, data clustering algorithms are considered as an essential component for data analysis. However, there has been limited research that addresses the challenges across Big Data and IoT and thus proposing a research agenda is important to clarify the research challenges for clustering Big Data in the context of IoT. By tackling this specific aspect - clustering algorithm in Big Data, this paper examines on Big Data technologies, related data clustering algorithms and possible usages in IoT. Based on our review, this paper identifies a set of research challenges that can be used as a research agenda for the Big Data clustering research. This research agenda aims at identifying and bridging the research gaps between Big Data clustering algorithms and IoT.
  • Angewandte Naturwissenschaften und Wirtschaftsingenieurwesen
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • M. Popescu
  • Mouzhi Ge
  • M. Helfert
The Social Media Perception and Reality – Possible Data Quality Deficiencies between Social Media and ERP, pg. 198-204.
  • 2018

DOI: 10.5220/0006788801980204

With the increase of digitalisation, data in social media are often seen as more updated and realistic than the information system representations. Due to the fast changes in the real world and the increasing Big Social media data, there is usually certain misalignment between the social media and information system in the enterprise such as ERP, therefore there can be data deficiencies or data quality problems in the information systems, which is caused by the differences between the external social media and internal information system. In this paper, underpinned by the work of ontological data quality from Wang and Wand 1996, we investigate a set of data quality problems between two representations Social Media and ERP. We further discuss how ERP system can be improved from the data quality perspective.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • P. Štěpánek
  • Mouzhi Ge
Validation and Extension of the Smart City Ontology, pg. 406-413.
  • 2018

DOI: 10.5220/0006818304060413

Over the last decade, the concept of the Smart City has been extensively studied with the development of modern societies. However, due to the complexity of Smart City, there does not exist a widely accepted definition for the Smart City. More recently, Ramaprasad et al. in 2017 have proposed a Smart City ontology that connects its relevant concepts with specified relations. This ontology thus can offer various paths by which theory and practice contribute to the development and understanding of a Smart City. However, this ontologyis still lacking practical validations to verify its applicability, Therefore, in this paper, we select a set of critical Smart City papers and validate this ontology by fitting the papers into this ontology. Based on the validations,we also further propose and discuss the possible extensions and consolidations for this Smart City Ontology.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • F. Persia
Evaluation in Multimedia Recommender Systems: A Practical Guide, pg. 294-297.
  • 2018

DOI: 10.1109/ICSC.2018.00050

With the widespread availability of media technologies, such as real-time streaming, new IoT devices and smartphones, multimedia data are extensively increased and the big multimedia data are rapidly spreaded over various social networks. Thus, different multimedia recommender systems have been emerging to help users select the useful multimedia objects. However, due to distinct features of multimedia objects, it is difficult to conduct a proper evaluation for the multimedia recommender systems, and the evaluation from the general recommender systems might not be totally adopted to evaluate them. In this paper, we therefore review and analyze the evaluation criteria that are used in the previous multimedia recommender system papers. Based on the review, we propose a set of the practical advices to lead practitioners and researchers to perform evaluations for multimedia recommender systems.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • A. Kobusinska
  • A. Wolski
  • J. Brzezinski
  • Mouzhi Ge
P2P Web Browser Middleware to Enhance Service Oriented Computing — Analysis and Evaluation, pg. 58-65.
  • 2017

DOI: 10.1109/SOCA.2017.16

The proliferation of web services and the wide choice of Web technologies has resulted in the increasing use of web browsers by service-oriented applications. To decrease the overloading of websites and thus make them more attractive for SOA applications, various solutions to deliver content and resources through web browsers are considered. Among existing approaches, WebRTC is used for the P2P content delivery networks. In this paper we conduct their comprehensive evaluation, compare their performance in multiple real-world use cases and to determine the practical application possibilities. We validate which P2P overlay can successfully deliver content and support web servers in reality.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • T. Chondrogiannis
Assessing the Quality of Spatio-Textual Datasets in the Absence of Ground Truth, pg. 12-20.
  • 2017
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • H. Bangui
  • Mouzhi Ge
  • B. Buhnova
  • S. Rakrak
  • S. Raghay
  • T. Pitner
Multi-Criteria Decision Analysis Methods in the Mobile Cloud Offloading Paradigm, vol. 6, pg. 25.
  • 2017

DOI: 10.3390/jsan6040025

Mobile cloud computing (MCC) is becoming a popular mobile technology that aims to augment local resources of mobile devices, such as energy, computing, and storage, by using available cloud services and functionalities. The offloading process is one of the techniques used in MCC to enhance the capabilities of mobile devices by moving mobile data and computation-intensive operations to cloud platforms. Several techniques have been proposed to perform and improve the efficiency and effectiveness of the offloading process, such as multi-criteria decision analysis (MCDA). MCDA is a well-known concept that aims to select the best solution among several alternatives by evaluating multiple conflicting criteria, explicitly in decision making. However, as there are a variety of platforms and technologies in mobile cloud computing, it is still challenging for the offloading process to reach a satisfactory quality of service from the perspective of customers’ computational service requests. Thus, in this paper, we conduct a literature review that leads to a better understanding of the usability of the MCDA methods in the offloading operation that is strongly reliant on the mobile environment, network operators, and cloud services. Furthermore, we discuss the challenges and opportunities of these MCDA techniques for offloading research in mobile cloud computing. Finally, we recommend a set of future research directions in MCDA used for the mobile cloud offloading process.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • Mouzhi Ge
  • F. Persia
A Survey of Multimedia Recommender Systems: Challenges and Opportunities, vol. 11, pg. 411-428.
  • 2017

DOI: 10.1142/S1793351X17500039

Multimedia information has been extensively growing from a variety of sources such as cameras or video recorders. In order to select the useful multimedia objects, multimedia recommender system has been emerging as a tool to help users choose which multimedia objects might be interesting for them. However, given the complexity of multimedia objects, it is challenging to provide effective multimedia recommendations. In this paper, we therefore conduct a survey in both the multimedia information system and recommender system communities. We further focus on the works that span the two communities, especially the research on multimedia recommender systems. Based on our review, we propose a set of research challenges, which can be used to implicate the future research directions for multimedia recommender systems. For each research challenge, we have also provided the insights of how to perform the follow-up research.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • D. Massimo
  • M. Elahi
  • Mouzhi Ge
  • F. Ricci
Item Contents Good, User Tags Better: Empirical Evaluation of a Food Recommender System, pg. 373-374.
  • 2017
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • F. Persia
Research Challenges in Multimedia Recommender Systems, pg. 344-347.
  • 2017

DOI: 10.1109/ICSC.2017.31

Nowadays, since multimedia information has been extensively growing from a variety of sources, such photos from social networks, unstructured text from different websites, or raw video feed from digital sensors, multimedia recommender system has been emerging as a tool to help users choose which multimedia objects might be interesting for them. However, given the complexity of multimedia, it is still challenging to provide effective recommendations, and research so far could only address limited aspects. Therefore, in this paper we propose a set of research challenges, which can be used to implicate the future research directions for multimedia recommender systems. For each research challenge, we have also provided the insights to explain which aspects are worth further investigation.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • T. OBrien
  • M. Helfert
Predicting Data Quality Success - The Bullwhip Effect in Data Quality, pg. 157-165.
  • 2017
Over the last years many data quality initiatives and suggestions report how to improve and sustain data quality. However, almost all data quality projects and suggestions focus on the assessment and one-time quality improvement, especially, suggestions rarely include how to sustain the continuous data quality improvement. Inspired by the work related to variability in supply chains, also known as the Bullwhip effect, this paper aims to suggest how to sustain data quality improvements and investigate the effects of delays in reporting data quality indicators. Furthermore, we propose that a data quality prediction model can be used as one of countermeasures to reduce the Data Quality Bullwhip Effect. Based on a real-world case study, this paper makes an attempt to show how to reduce this effect. Our results indicate that data quality success is a critical practice, and predicting data quality improvements can be used to decrease the variability of the data quality index in a long run.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • P. Štěpánek
  • Mouzhi Ge
  • L. Walletzký
IT-Enabled Digital Service Design Principles - Lessons Learned from Digital Cities, pg. 186-196.
  • 2017
With the rapid expansion of emerging digital technologies, digital service creation and delivery demand new and more structured ways to design, develop and manage the service sustainability. Although, there are various views and strategic aspects from different stakeholders for designing the digital services, the clear answer specifying how to design the digital service within IT architectures or how to re-use design processes learned from service design used in previous Digital City projects is still unknown. In order to derive the digital service design principles, we study the IT architectures that are related to digital services and revisit one typical Digital City - Barcelona. Based on the lessons learned from the Digital City project, we propose a set of design principles that can guide researchers and practitioners to design the digital services in a Digital City.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • A. Khalilijafarabad
  • M. Helfert
  • Mouzhi Ge
Developing a Data Quality Research Taxonomy - an organizational perspective, pg. 176-186.
  • 2016
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • M. Helfert
  • Mouzhi Ge
Big Data Quality - Towards an Explanation Model, pg. 16-23.
  • 2016
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • M. Elahi
  • Mouzhi Ge
  • F. Ricci
  • I. Fernández-Tobías
  • S. Berkovsky
  • D. Massimo
Interaction Design in a Mobile Food Recommender System, pg. 49-52.
  • 2015
One of the most important steps in building a recommender system is the interaction design process, which defines how the recommender system interacts with a user. It also shapes the experience the user gets, from the point she registers and provides her preferences to the system, to the point she receives recommendations generated by the system. A proper interaction design may improve user experience and hence may result in higher usability of the system, as well as, in higher satisfaction. In this paper, we focus on the interaction design of a mobile food recommender system that, through a novel interaction process, elicits users’ long-term and short-term preferences for recipes. User’s long-term preferences are captured by asking the user to rate and tag familiar recipes, while for collecting the short-term preferences, the user is asked to select the ingredients she would like to include in the recipe to be prepared. Based on the combined exploitation of both types of preferences, a set of personalized recommendations is generated. We conducted a user study measuring the usability of the proposed interaction. The results of the study show that the majority of users rates the quality of the recommendations high and the system achieves usability scores above the standard benchmark.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • M. Elahi
  • I. Fernaández-Tobías
  • F. Ricci
  • D. Massimo
Using Tags and Latent Factors in a Food Recommender System, pg. 105-112.
  • 2015

DOI: 10.1145/2750511.2750528

Due to the extensive growth of food varieties, making better and healthier food choices becomes more and more complex. Most of the current food suggestion applications offer just generic advices that are not tailored to the user's personal taste. To tackle this issue, we propose in this paper a novel food recommender system that provides high quality and personalized recipe suggestions. These recommendations are generated by leveraging a data set of users' preferences expressed in the form of users' ratings and tags, which signal the food's ingredients or features that the users like. Our empirical evaluation shows that the proposed recommendation technique significantly outperforms state-of-the-art algorithms. We have found that using tags in food recommendation algorithms can significantly increase the prediction accuracy, i.e., the match of the predicted preferences with the true user's preferred recipes. Furthermore, our user study shows that our system prototype is of high usability.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • F. Ricci
  • D. Massimo
Health-aware Food Recommender System, pg. 333-334.
  • 2015

DOI: 10.1145/2792838.2796554

With the rapid changes in the food variety and lifestyles, many people are facing the problem of making healthier food decisions to reduce the risk of chronic diseases such as obesity and diabetes. To this end, our recommender system not only offers recipe recommendations that suit the user's preference but is also able to take the user's health into account. It is developed on a mobile platform by considering that our application may be directly used in the kitchen. This demo paper summarizes the complete human-computer interaction design, the implemented health-aware recommendation algorithm and preliminary user feedback.
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • Mouzhi Ge
  • M. Helfert
Impact of Information Quality on Supply Chain Decisions, vol. 53, pg. 59-67.
  • 2015

DOI: 10.1080/08874417.2013.11645651

A number of studies suggest that making correct decisions depends on high-quality information; how information quality affects decision-making is still not fully understood. Following the multi-dimensional view of information quality, this paper investigates the effects of information accuracy, completeness, and consistency on decision-making. Results show that information accuracy and completeness affect decision quality significantly. Although the effect of information consistency on decision quality appears to be non-significant, consistency of information may intensify the contribution of accuracy, indicating that information accuracy and consistency influence decision quality jointly.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • M. Braunhofer
  • M. Elahi
  • Mouzhi Ge
  • F. Ricci
Context Dependent Preference Acquisition with Personality-Based Active Learning in Mobile Recommender Systems, pg. 105-116.
  • 2014
Nowadays, Recommender Systems (RSs) play a key role in many businesses. They provide consumers with relevant recommendations, e.g., Places of Interest (POIs) to a tourist, based on user preference data, mainly in the form of ratings for items. The accuracy of recommendations largely depends on the quality and quantity of the ratings (preferences) provided by the users. However, users often tend to rate no or only few items, causing low accuracy of the recommendation. Active Learning (AL) addresses this problem by actively selecting items to be presented to the user in order to acquire a larger number of high-quality ratings (preferences), and hence, improve the recommendation accuracy. In this paper, we propose a personalized active learning approach that leverages user’s personality data to get more and better in-context ratings. We have designed a novel human computer interaction and assessed our proposed approach in a live user study - which is not common in active learning research. The main result is that the system is able to collect better ratings and provide more relevant recommendations compared to a variant that is using a state of the art approach to preference acquisition.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • M. Helfert
A Design Science Oriented Framework for Experimental Research in Information Quality, pg. 145-154.
  • 2014
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • M. Elahi
  • Mouzhi Ge
  • F. Ricci
  • D. Massimo
  • S. Berkovsky
Interactive Food Recommendation for Groups
  • 2014
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • F. Gedikli
  • D. Jannach
  • Mouzhi Ge
How should I explain? A comparison of different explanation types for recommender systems, vol. 72, pg. 367-382.
  • 2014

DOI: 10.1016/j.ijhcs.2013.12.007

Recommender systems help users locate possible items of interest more quickly by filtering and ranking them in a personalized way. Some of these systems provide the end user not only with such a personalized item list but also with an explanation which describes why a specific item is recommended and why the system supposes that the user will like it. Besides helping the user understand the output and rationale of the system, the provision of such explanations can also improve the general acceptance, perceived quality, or effectiveness of the system. In recent years, the question of how to automatically generate and present system-side explanations has attracted increased interest in research. Today some basic explanation facilities are already incorporated in e-commerce Web sites such as Amazon.com. In this work, we continue this line of recent research and address the question of how explanations can be communicated to the user in a more effective way. In particular, we present the results of a user study in which users of a recommender system were provided with different types of explanation. We experimented with 10 different explanation types and measured their effects in different dimensions. The explanation types used in the study include both known visualizations from the literature as well as two novel interfaces based on tag clouds. Our study reveals that the content-based tag cloud explanations are particularly helpful to increase the user-perceived level of transparency and to increase user satisfaction even though they demand higher cognitive effort from the user. Based on these insights and observations, we derive a set of possible guidelines for designing or selecting suitable explanations for recommender systems.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • M. Helfert
Cost and Value Management for Data Quality, pg. 75-92.
  • 2013
  • Europan Campus Rottal-Inn
Beitrag (Sammelband oder Tagungsband)
  • K. Stoll
  • Mouzhi Ge
  • M. Hepp
Understanding the Impact of E-Commerce Software on the Adoption of Structured Data on the Web, pg. 100-112.
  • 2013
  • Europan Campus Rottal-Inn
Beitrag (Sammelband oder Tagungsband)
  • M. Braunhofer
  • M. Elahi
  • Mouzhi Ge
  • F. Ricci
  • T. Schievenin
STS: Design of Weather-Aware Mobile Recommender Systems in Tourism
  • 2013
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • B. Rodriguez-Castro
  • Mouzhi Ge
  • M. Hepp
Alignment of Ontology Design Patterns: Class As Property Value, Value Partition and Normalisation, pg. 682-699.
  • 2012
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • A. Borek
  • M. Helfert
  • Mouzhi Ge
  • A. Parlikad
IS/IT Resources and Business Value: Operationalization of an Information Oriented Framework, pg. 420-434.
  • 2012
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • D. Jannach
  • F. Gedikli
Bringing Diversity to Recommendation Lists - An Analysis of the Placement of Diverse Items, pg. 293-305.
  • 2012
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • D. Jannach
  • M. Zanker
  • Mouzhi Ge
  • M. Gröning
Recommender Systems in Computer Science and Information Systems - A Landscape of Research, pg. 76-87.
  • 2012
The paper reviews and classifies recent research in recommender systems both in the field of Computer Science and Information Systems. The goal of this work is to identify existing trends, open issues and possible directions for future research. Our analysis is based on a review of 330 papers on recommender systems, which were published in high-impact conferences and journals during the past five years (2006-2011). We provide a state-of-the-art review on recommender systems, propose future research opportunities for recommender systems in both computer science and information system community, and indicate how the research avenues of both communities might partly converge.
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • D. Jannach
  • F. Gedikli
  • M. Hepp
Effects of the Placement of Diverse Items in Recommendation Lists, pg. 201-208.
  • 2012
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • F. Gedikli
  • D. Jannach
Placing High-Diversity Items in Top-N Recommendation Lists
  • 2011
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • A. Borek
  • A. Parlikad
  • M. Helfert
  • Mouzhi Ge
An Information Oriented Framework for Relating IS/IT Resources and Business Value, pg. 358-367.
  • 2011
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • Mouzhi Ge
  • M. Helfert
  • D. Jannach
Information quality assessment: validating measurement dimensions and processes, pg. 75.
  • 2011
  • Europan Campus Rottal-Inn
  • DIGITAL
Beitrag (Sammelband oder Tagungsband)
  • F. Gedikli
  • Mouzhi Ge
  • D. Jannach
Understanding Recommendations by Reading the Clouds, pg. 196-208.
  • 2011
  • Europan Campus Rottal-Inn
  • DIGITAL
Zeitschriftenartikel
  • F. Gedikli
  • Mouzhi Ge
  • D. Jannach
Explaining Online Recommendations Using Personalized Tag Clouds, vol. 10, pg. 3-10.
  • 2011

DOI: 10.1524/icom.2011.0002

Recommender systems are sales-supporting applications that are usually integrated into online shops and are designed to point the visitor to products or services she or he might be interested in but has not bought yet. In the last decade, many techniques have been developed to improve the predictive accuracy of such systems. However, there are also factors other than accuracy that infl uence the user-perceived quality of such a system. In particular, system-generated explanations as to why a certain item has been recommended have shown to be a valuable tool to improve both the user's satisfaction and the system's effi ciency. This paper reports the results of a fi rst user study which was conducted to evaluate whether personalized tag clouds are an appropriate means to visually explain recommendations. The evaluation reveals that using tag clouds as explanation mechanism leads to higher user satisfaction and recommendation effi ciency than previous keyword-style explanations.
  • Europan Campus Rottal-Inn
  • DIGITAL

Vita

Dr. Mouzhi Ge is a Professor for Data Analytics at the Deggendorf Institute of Technology in Germany. He was previously an Associate Professor (Tenured) at the Masaryk University in Czech Republic, where he obtained his Habilitation. He received his Ph.D. from Dublin City University in Ireland. Afterwards he has conducted research and practice on data engineering and intelligent systems in Germany, USA and Italy. His research is mainly focused on Big Data Analytics, Intelligent Healthcare Systems, Internet of Things and Health-aware Recommender Systems. Within those research areas he has published more than 100 research papers. Over the last 10 years, his works have been published in a variety of journals such as Future Generation Computer Systems, International Journal of Human-Computer Studies, International Journal of Cooperative Information Systems, IEEE Access, Wireless Personal Communications, International Journal of Semantic Computing, Internet of Things Journal, Journal of Sensor and Actuator Networks, Journal of Computer Information Systems etc.