Context-based Services Research Articles

Dynamic User Activity Prediction using Contextual Service Matching Mechanism

The significance of context-based services is significantly increasing with the advancement of integrated technologies of sensors and ubiquitous technologies. The existing approaches are reviewed to find out that identification of user's activity has more scope of improvement. After reviewing the current literature towards context-based methodologies, it is found that existing methods are devoid of considering dynamic context; while the modelling perspective is mainly towards considering predefined and static contextual information. Further, existing models doesn't have any inclusion of potential belief system nor any incorporation of service matching. Further, practical world case-studies is characterized by complex activity of user while it is quite challenging to extract the accurate contextual information associated with complex user activity. From the practical deployment scenario, the existing system offers less supportability toward collaborative network, which is highly essential to be considered for constraint modelling for user activity detection. Therefore, the proposed manuscript contributes a solution towards existing research problems by introducing a Dynamic User Activity Prediction using Contextual Service Matching Mechanism. A mixed research methodology is used to prove how service matching mechanism is important in contextual service discovery using multimodal activity data. The first contributory solution towards addressing the research problem is by introducing a novel and simplified belief system that considers both static contextual parameters as well as dynamic activity-based contextual parameter. The second contributory solution towards existing problem is to develop a novel service matching module that takes the input from service reposit, user calendar events, and collaborative units for assisting in similarity-based recommendation system. The model considers Hidden Markov Model for activity determination considering states of activity. With a combined usage of user activity context, feature management, and collaborative model, the proposed system offers better granularity in investigating user activity. The experimental and simulation analysis of the proposed outcome shows the enhanced accuracy performance of proposed system under different test environment. The study also investigates the impact of the service matching mechanism as well as relevance feedback on the accuracy to find that the proposed system excels better accuracy.

Multi-agent cognitive architecture-enabled IoT applications of mobile edge computing

Mobile edge computing (MEC) offers cloud capabilities and service environment for Internet-of-Things (IoT) applications at the edge of the mobile network. New services for a specific set of IoT application programming interfaces (APIs) of diversified industry verticals can efficiently be deployed. As the set of APIs based on the IoT continues to thrive, reliance on the underlying cloud computing to deliver real-time and context-based services is also prominent in MEC. Due to the increased level of mutual interference of IoT APIs, the complexities are also multiplied. The set of IoT APIs competes for available resources within heterogeneous clouds (HCs). It is further aggravated by the unprecedented number of connected devices. We are presenting a cognitive agent (CA)-oriented approach to proactively subordinate IoT APIs with HCs. This paper contributes to establish an empirical multi-agent cognitive architecture framework (MCAF) for continuous transition of IoT APIs. We identified an adaptable composition method and a classification technique for CAs during this research effort. It introduces rationalization of CA creation, migration, and control. The approach achieves transparency in the heterogeneity and distribution of IoT APIs. It provides dynamism of cloud computing environments. The paper also illustrates the architecture impact analysis with the indicative capabilities of auto-scaling, predictability in HCs’ resource use, and responsiveness and attainment of IoT APIs.

Cognitive Privacy Middleware for Deep Learning Mashup in Environmental IoT

Data mashup is a Web technology that combines information from multiple sources into a single Web application. Mashup applications support new services, such as environmental monitoring. The different organizations utilize data mashup services to merge data sets from the different Internet of Multimedia Things (IoMT) context-based services in order to leverage the performance of their data analytics. However, mashup, different data sets from multiple sources, is a privacy hazard as it might reveal citizens specific behaviors in different regions. In this paper, we present our efforts to build a cognitive-based middleware for private data mashup (CMPM) to serve a centralized environmental monitoring service. The proposed middleware is equipped with concealment mechanisms to preserve the privacy of the merged data sets from multiple IoMT networks involved in the mashup application. In addition, we presented an IoT-enabled data mashup service, where the multimedia data are collected from the various IoMT platforms, and then fed into an environmental deep learning service in order to detect interesting patterns in hazardous areas. The viable features within each region were extracted using a multiresolution wavelet transform, and then fed into a discriminative classifier to extract various patterns. We also provide a scenario for IoMT-enabled data mashup service and experimentation results.

Quantitative Study of Music Listening Behavior in a Smartphone Context

Context-based services have attracted increasing attention because of the prevalence of sensor-rich mobile devices such as smartphones. The idea is to recommend information that a user would be interested in according to the user’s surrounding context. Although remarkable progress has been made to contextualize music playback, relatively little research has been made using a large collection of real-life listening records collected in situ . In light of this fact, we present in this article a quantitative study of the personal, situational, and musical factors of musical preference in a smartphone context, using a new dataset comprising the listening records and self-report context annotation of 48 participants collected over 3wk via an Android app. Although the number of participants is limited and the population is biased towards students, the dataset is unique in that it is collected in a daily context, with sensor data and music listening profiles recorded at the same time. We investigate 3 core research questions evaluating the strength of a rich set of low-level and high-level audio features for music usage auto-tagging (i.e., music preference in different user activities), the strength of time-domain and frequency-domain sensor features for user activity classification, and how user factors such as personality traits are correlated with the predictability of music usage and user activity, using a closed set of 8 activity classes. We provide an in-depth discussion of the main findings of this study and their implications for the development of context-based music services for smartphones.

Augmented context-based recommendation service framework using knowledge over the Linked Open Data cloud

This research proposes ACARDS (Augmented-Context bAsed RecommenDation Service) framework that is able to utilize knowledge over the Linked Open Data (LOD) cloud to recommend context-based services to users. To improve the level of user satisfaction with the result of the recommendation, the ACARDS framework implements a novel recommendation algorithm that can utilize the knowledge over the LOD cloud. In addition, the noble algorithm is able to use new concepts like the enriched tags and the augmented tags that originate from the hashtags on the SNSs materials. These tags are utilized to recommend the most appropriate services in the user’s context, which can change dynamically. Last but not least, the ACARDS framework implements the context-based reshaping algorithm on the augmented tag cloud. In the reshaping process, the ACARDS framework can recommend the highly receptive services in the users’ context and their preferences. To evaluate the performance of the ACARDS framework, we conduct four kinds of experiments using the Instagram materials and the LOD cloud. As a result, we proved that the ACARDS framework contributes to increasing the query efficiency by reducing the search space and improving the user satisfaction on the recommended services.

Mobile App Classification with Enriched Contextual Information

The study of the use of mobile Apps plays an important role in understanding the user preferences, and thus provides the opportunities for intelligent personalized context-based services. A key step for the mobile App usage analysis is to classify Apps into some predefined categories. However, it is a nontrivial task to effectively classify mobile Apps due to the limited contextual information available for the analysis. For instance, there is limited contextual information about mobile Apps in their names. However, this contextual information is usually incomplete and ambiguous. To this end, in this paper, we propose an approach for first enriching the contextual information of mobile Apps by exploiting the additional Web knowledge from the Web search engine. Then, inspired by the observation that different types of mobile Apps may be relevant to different real-world contexts, we also extract some contextual features for mobile Apps from the context-rich device logs of mobile users. Finally, we combine all the enriched contextual information into the Maximum Entropy model for training a mobile App classifier. To validate the proposed method, we conduct extensive experiments on 443 mobile users' device logs to show both the effectiveness and efficiency of the proposed approach. The experimental results clearly show that our approach outperforms two state-of-the-art benchmark methods with a significant margin.

USING SNS DATA IN PREDICTION OF TV VIEWERSHIP

ABSTRACT Social Network Sites (SNS), the web-based services, to construct individual profile either publically or privately, share the connections formed among individual relations, and support interactivity brought from those connections (Boyd and Ellison 2008). The state of the usage of SNS by type in Korea is as follows; blog 84.4%, community 74.6%, mini-homepage 68.3%, profile-based service 18.4%, and micro-blog 12.8% in descending order (Korea Communications Commission and Korea Internet Security Agency 2012). Since the analyzing of the massive content data and related network information through SNS became possible, efforts to find and utilize new meaning have recently grown active as well. Thus, as “Big data era” advents, firms are maximizing profit through customized services with big data analysis. Big data imply database with mega-capacity that exceeds the scope of existing database that can store, manage, and analyze. It is the formal or informal data that cannot be collected, stored, retrieved, analyzed, and visualized through existing methods or tools (McKinsey Global Institute 2011). Using big data can provide customized context-based services to each customer and improve customer satisfaction. For example, on December 18th – the day before Korean presidential election, the ratio of people’s data search amount on Google for the two candidates were 52.6% for Park, and 47.3% for Moon, which closely matched the actual ratio of 51.6% to 48% (www.chosun.com accessed 2012). The behavior consuming media is evolving from consuming through individualized media to social consumption, meaning participation and sharing. The viewers no longer remain just ‘passive viewers’. They also give out opinions while viewing programs and share information or feeling about the program before and after viewing. Such “Social TV” is spreading out, and therefore, complementing relation needs to be formed in addition to existing statistical survey by catching real-time feedbacks through SNS or blog analysis to understand the trend. If influencing power of on-line data as independent variable can be predicted for viewing rate data, then the viewing rate prediction for contents that takes costly production budget and establishing a corresponding marketing strategy will be much easier. Nowadays, it covers approximately 0.2 to 0.5 million dollars per episode to produce a mini-series drama in Korean media industry. One title usually consists of 16 to 20 episodes. Thus, total investment takes about 3 to 9.3 million dollars. So far, the only quantitative measurement tool that broadcasting organizations, producing companies, merchandising providers, and advertisers use to measure the outcome of their investment production is viewer rating data. With “Han-ryu,” the Korean culture power spreading globally through K-pop and Korean drama, an analyzing system that can diminish investors’ risk, maximize the marketing effect, and swiftly execute strategy into practice will contribute greatly in producing high-quality contents. In Korea, it is pretty rare that television programs are fully produced in advance. Most of the programs go through final editing by episodes about a week before broadcasting. If marketability of contents can be grasped, it will be more convenient to determine (1) whether to stick to the original plan and invest persistently, (2) whether to adjust the investment plan according to viewers’ response, or (3) whether to completely put a stop to investment or broadcasting in short amount of time. The purpose of this study is to predict viewers’ responses that can be evaluated as viewing rate by analyzing big data buzzword pattern related to the contents created and accumulated on-line during or after the broadcasting of programs. The construction of this study begins with literature review and suppositions setting from the attributes of gathered data. Analyzing tools and the contents that are to be analyzed are presented in the third section. In the fourth section, reliability analysis, primary component analysis, and regression analysis are conducted for the model. Finally, the last section summarizes the results and reaches the conclusion of this study with proper suggestions.

Privacy-by-design rules in face recognition system

In this paper, we develop a face recognition system based on softcomputing techniques, which complies with privacy-by-design rules and defines a set of principles that are context-aware applications (including biometric sensors) and should contain to conform to European and US law. This paper deals with the necessity to consider legal issues concerning privacy or human rights in the development of biometric identification in ambient intelligence systems. Clearly, context-based services and ambient intelligence (and the most promising research area in Europe, namely ambient assisted living, ALL) call for a major research effort on new identification procedures.

Developing Advanced Context Aware Tools for Mobile Maintenance

The rapid technological progress in the domains of wireless sensor networks, mobile application development and computational intelligence has fueled the construction of "smart" environments in both domestic and industrial settings. Such environments are equipped with a wide range of sensors, identification tags and interaction devices, capable of sensing, recording, interpreting and reacting to human activity and presence. Context-awareness constitutes a major challenge for developers of smart services, since both design and implementation are increasingly supported by widely adopted frameworks and well-structured tools. The value adding features of context-based services find their way into many industrial systems through the adoption of mobile computing. Acting as a constant context monitoring agent, a tablet or a smartphone can expand the capacity of a shoop floor system actor to carry out asset management tasks. Context interpretation and system adaptation are highly specialized processes that essentially use predefined or dynamically build semantics to filter and configure the mobile actor's access session. In this paper we discuss the context semantics for an IT infrastructure that serves engineering asset management and specifically supports maintenance practice and planning. Evaluating the available software methodologies that can drive the implementation of such an infrastructure, we perform a suitability study for the development of a maintenance management and a condition monitoring portable client. Our goal is to identify and assess the weighted significance for a domain-focused set of functional parameters, used to define a context-based mobile tool scaled for industrial shop-floor complexity.

Opportunities in the Mobile Search Market

Success in the mobile search market will come to those who provide value-added apps that exploit unique mobile functionalities, especially those related to personalized and context-based services.

Exploring the logic of mobile search

After more than a decade of development work and hopes, the usage of mobile Internet has finally taken off. Now, we are witnessing the first signs of evidence of what might become the explosion of mobile content and applications that will be shaping the (mobile) Internet of the future. Similar to the wired Internet, search will become very relevant for the usage of mobile Internet. Current research on mobile search has applied a limited set of methodologies and has also generated a narrow outcome of meaningful results. This article covers new ground, exploring the use and visions of mobile search with a users' interview-based qualitative study. Its main conclusion builds upon the hypothesis that mobile search is sensitive to a mobile logic different than today's one. First, (advanced) users ask for accessing with their mobile devices the entire Internet, rather than subsections of it. Second, success is based on new added-value applications that exploit unique mobile functionalities. The authors interpret that such mobile logic involves fundamentally the use of personalised and context-based services.

Guest editorial: content, concept and context mining in social media

In the last few years, we have witnessed an exponentially growing amount of social media data from social networks, mainly driven by the huge popularity of Web and the rapid advances of multimedia and Internet technologies. Different from conventional data types, social media data are multi-model in nature, including content such as images, audio, and videos, concept such as discussion topic, tag, and annotation, and context such as links, profile, timestamp, and click-through. All these content, concept and context are essential data sources for mining semantics, user intents, trends, knowledge, etc., from social media data, as well as enabling intelligent applications on social media services. This rich media type has raised many new research challenges, ranging from large-scale social media content analysis and mining, concept discovery and monitoring, context-based services, to many other exciting new opportunities. The aim of this special issue is to bring out state-of-the-art research in this area and discover directions for future research. The special issue will serve as a forum for recent advances in the field, with an emphasis on mining the “3 C” (Content, Concept and Context). It received an enthusiastic response. Among 19 submissions, 5 papers were selected after several rounds of rigorous review by the guest editors and the invited reviewers. World Wide Web (2012) 15:115–116 DOI 10.1007/s11280-011-0142-4

Meetings through the cloud: Privacy-preserving scheduling on mobile devices

Abstract Mobile devices are increasingly being used to store and manage users’ personal information, as well as to access popular third-party context-based services. Very often, these applications need to determine common availabilities among a set of user schedules, in order to allow colleagues, business partners and people to meet. The privacy of the scheduling operation is paramount to the success of such applications, as often users do not want to share their personal schedule details with other users or third-parties. In this paper, we propose practical and privacy-preserving solutions for mobile devices to the server-based scheduling problem. Our three novel algorithms take advantage of the homomorphic properties of well-known cryptosystems in order to privately and efficiently compute common user availabilities. We also formally outline the privacy requirements in such scheduling applications and we implement our solutions on real mobile devices. The experimental measurements and analytical results show that the proposed solutions not only satisfy the privacy properties but also fare better, in regard to computation and communication efficiency, compared to other well-known solutions. Finally, we assess the utility and expectations, in terms of privacy and usability, of the proposed solutions by means of a targeted survey and user-study of mobile-phone users.

Design and implementation of a device-independent system for adaptive composition of web services

The modularity of web services has left an open problem in composition – a scenario that involves an amalgamation of two or more web services to fulfil a request that no one web service is able to provide. This paper presents the design and implementation of a system that enables users of any device to dynamically discover context-based web services that will be automatically composed to satisfy a user's request. Existing web services can be easily adapted and new web services can be easily deployed. The system uses a custom UDDI-like registry that we have designed and implemented to support context-based adaptive composition.

A FRAMEWORK FOR ADAPTIVE AND DYNAMIC COMPOSITION OF WEB SERVICES

The modularity of web services has left an open problem in composition, a scenario that involves an amalgamation of two or more web services to fulfill a request that no one web service is able to provide. This paper presents a framework for adaptive and dynamic composition of web services, enabling web services to be discovered either statically or dynamically by utilizing a semantic ontology to describe web services and their methods. This novel approach gives greater control on how web services are dynamically discovered by allowing the application developer to specify how matches are made, which goes beyond the present techniques of semantically matching inputs and outputs along with classification taxonomies. We utilize the Composite Capabilities/Preferences Profiles (CC/PP) to adapt the interface and content to be compatible with virtually any device. A proof of concept implementation has been constructed that enables users of any device to dynamically discover context-based services that will be dynamically composed to satisfy a user's request. In addition, we have designed and implemented a UDDI-like registry to support context-based adaptive composition of web services. Existing web services can be easily adapted and new web services can be effortlessly deployed.

Location-Based Services in Mobile Communication Infrastructures

Summary Location- and context-based services form a new class of services, which supplement existing services in the mobile communication infrastructure. The paper describes shortly an architecture of systems supporting the new class of services; this architecture extends beyond those systems which have initially been introduced by support of centralized data bases (such as web servers) and by federation components providing search and mapping functions which are necessary for the full exploitation of the capabilities of such services. The concept is based on the existence of heterogeneous mobile and radio access networks. The question arises, among others, to what extent such services add to the network load and its performance, in particular the question of scalability. In this paper, an approach is outlined as a basis for future capacity planning and for the support of strategic decision making with respect to infrastructure investments.