scholarly journals Normalizing Item-Based Collaborative Filter Using Context-Aware Scaled Baseline Predictor

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Wenming Ma ◽  
Junfeng Shi ◽  
Ruidong Zhao
Keyword(s):  
Recommendation Systems ◽  
Basic Component ◽  
Experimental Results ◽  
Context Information ◽  
Context Aware ◽  
Collaborative Filter ◽  
Normalization Methods ◽  
Predictor Models ◽  
Baseline Predictor ◽  
Filter Algorithms

Item-based collaborative filter algorithms play an important role in modern commercial recommendation systems (RSs). To improve the recommendation performance, normalization is always used as a basic component for the predictor models. Among a lot of normalizing methods, subtracting the baseline predictor (BLP) is the most popular one. However, the BLP uses a statistical constant without considering the context. We found that slightly scaling the different components of the BLP separately could dramatically improve the performance. This paper proposed some normalization methods based on the scaled baseline predictors according to different context information. The experimental results show that using context-aware scaled baseline predictor for normalization indeed gets better recommendation performance, including RMSE, MAE, precision, recall, and nDCG.

scholarly journals Context-Aware Attention Network for Human Emotion Recognition in Video

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Xiaodong Liu ◽  
Miao Wang
Keyword(s):  
Facial Expression ◽  
Emotion Recognition ◽  
Recognition Accuracy ◽  
Experimental Results ◽  
The Other ◽  
Context Information ◽  
Context Aware ◽  
Attention Network ◽  
Human Emotion ◽  
Video Frames

Recognition of human emotion from facial expression is affected by distortions of pictorial quality and facial pose, which is often ignored by traditional video emotion recognition methods. On the other hand, context information can also provide different degrees of extra clues, which can further improve the recognition accuracy. In this paper, we first build a video dataset with seven categories of human emotion, named human emotion in the video (HEIV). With the HEIV dataset, we trained a context-aware attention network (CAAN) to recognize human emotion. The network consists of two subnetworks to process both face and context information. Features from facial expression and context clues are fused to represent the emotion of video frames, which will be then passed through an attention network and generate emotion scores. Then, the emotion features of all frames will be aggregated according to their emotional score. Experimental results show that our proposed method is effective on HEIV dataset.

A Collaborative Filtering Recommendation Algorithm Incorporated with Life Cycle

2013 ◽  
Vol 765-767 ◽  
pp. 630-633 ◽  
Author(s):  
Chong Lin Zheng ◽  
Kuang Rong Hao ◽  
Yong Sheng Ding
Keyword(s):  
Life Cycle ◽  
Collaborative Filtering ◽  
Recommendation Systems ◽  
Experimental Results ◽  
User Interest ◽  
Recommendation Algorithm ◽  
Time Information ◽  
Successful Technology

Collaborative filtering recommendation algorithm is the most successful technology for recommendation systems. However, traditional collaborative filtering recommendation algorithm does not consider the change of time information. For this problem,this paper improve the algorithm with two new methods:Predict score incorporated with time information in order to reflect the user interest change; Recommend according to scores by adding the weight information determined by the item life cycle. Experimental results show that the proposed algorithm outperforms the traditional item in accuracy.

Stream-based explainable recommendations via blockchain profiling

2021 ◽  
pp. 1-17
Author(s):  
Fátima Leal ◽  
Bruno Veloso ◽  
Benedita Malheiro ◽  
Juan Carlos Burguillo ◽  
Adriana E. Chis ◽  
...  
Keyword(s):  
Historical Data ◽  
Positive Impact ◽  
Empirical Evaluation ◽  
Recommendation Systems ◽  
Use Cases ◽  
Collaborative Filter ◽  
Model Based ◽  
Collaborative Recommendation ◽  
Smart Contract ◽  
User Trust

Explainable recommendations enable users to understand why certain items are suggested and, ultimately, nurture system transparency, trustworthiness, and confidence. Large crowdsourcing recommendation systems ought to crucially promote authenticity and transparency of recommendations. To address such challenge, this paper proposes the use of stream-based explainable recommendations via blockchain profiling. Our contribution relies on chained historical data to improve the quality and transparency of online collaborative recommendation filters – Memory-based and Model-based – using, as use cases, data streamed from two large tourism crowdsourcing platforms, namely Expedia and TripAdvisor. Building historical trust-based models of raters, our method is implemented as an external module and integrated with the collaborative filter through a post-recommendation component. The inter-user trust profiling history, traceability and authenticity are ensured by blockchain, since these profiles are stored as a smart contract in a private Ethereum network. Our empirical evaluation with HotelExpedia and Tripadvisor has consistently shown the positive impact of blockchain-based profiling on the quality (measured as recall) and transparency (determined via explanations) of recommendations.

scholarly journals Context-Aware Human Activity Recognition in Industrial Processes

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 134
Author(s):  
Friedrich Niemann ◽  
Stefan Lüdtke ◽  
Christian Bartelt ◽  
Michael ten Hompel
Keyword(s):  
Activity Recognition ◽  
Time Management ◽  
Recognition Performance ◽  
Context Information ◽  
Context Aware ◽  
Recognition Model ◽  
Movement Data ◽  
Information Activity ◽  
The Subject ◽  
Motion Capturing

The automatic, sensor-based assessment of human activities is highly relevant for production and logistics, to optimise the economics and ergonomics of these processes. One challenge for accurate activity recognition in these domains is the context-dependence of activities: Similar movements can correspond to different activities, depending on, e.g., the object handled or the location of the subject. In this paper, we propose to explicitly make use of such context information in an activity recognition model. Our first contribution is a publicly available, semantically annotated motion capturing dataset of subjects performing order picking and packaging activities, where context information is recorded explicitly. The second contribution is an activity recognition model that integrates movement data and context information. We empirically show that by using context information, activity recognition performance increases substantially. Additionally, we analyse which of the pieces of context information is most relevant for activity recognition. The insights provided by this paper can help others to design appropriate sensor set-ups in real warehouses for time management.

scholarly journals Study of a Context Quality Model for UbiPri Middleware

2020 ◽  
Author(s):  
Diandre de Paula ◽  
Daniel Saraiva ◽  
Romeiro Natália ◽  
Nuno Garcia ◽  
Valderi Leithardt
Keyword(s):  
Quality Indicators ◽  
Data Privacy ◽  
Context Information ◽  
Adaptation Process ◽  
Context Aware ◽  
Quality Model ◽  
Context Aware Computing ◽  
Quality Of Context ◽  
The Impact

With the growth of ubiquitous computing, context-aware computing-based applications are increasingly emerging, and these applications demonstrate the impact that context has on the adaptation process. From the context, it will be possible to adapt the application according to the requirements and needs of its users. Therefore, the quality of the context information must be guaranteed so that the application does not have an incorrect or unexpected adaptation process. But like any given data, there is the possibility of inaccuracy and/or uncertainty and so Quality of Context (QoC) plays a key role in ensuring the quality of context information and optimizing the adaptation process. To guarantee the Quality of Context it is necessary to study a quality model to be created, which will have the important function of evaluating the context information. Thus, it is necessary to ensure that the parameters and quality indicators to be used and evaluated are the most appropriate for a given type of application. This paper aims to study a context quality model for the UbiPri middleware, defining its quality indicators to ensure its proper functioning in the process of adaptation in granting access to ubiquitous environments. Keywords: QoC, Model, Context-Aware, Data, Privacy

Evaluation of Quality of Context Information in U-Health Smart Homes

2012 ◽  
pp. 179-215 ◽  
Author(s):  
José Bringel Filho ◽  
Nazim Agoulmine
Keyword(s):  
Health Systems ◽  
Smart Homes ◽  
Well Being ◽  
Context Information ◽  
Context Aware ◽  
Daily Lives ◽  
Quality Of Context ◽  
The Impact ◽  
Health And Well Being

Ubiquitous Health (U-Health) smart homes are intelligent spaces capable of observing and correctly recognizing the activities and health statuses of their inhabitants (context) to provide the appropriate support to achieve an overall sense of health and well-being in their inhabitants’ daily lives. With the intrinsic heterogeneity and large number of sources of context information, aggregating and reasoning on low-quality raw sensed data may result in conflicting and erroneous evaluations of situations, affecting directly the reliability of the U-Health systems. In this environment, the evaluation and verification of Quality of Context (QoC) information plays a central role in improving the consistency and correctness of context-aware U-Health applications. Therefore, the objective of this chapter is to highlight the impact of QoC on the correct behavior of U-Health systems, and introduce and analyze the existing approaches of modeling, evaluating, and using QoC to improve its context-aware decision-making support.

Service Selection with Uncertain Context Information

2012 ◽  
pp. 192-215 ◽  
Author(s):  
Yves Vanrompay ◽  
Manuele Kirsch-Pinheiro ◽  
Yolande Berbers
Keyword(s):  
Real Life ◽  
Similarity Measures ◽  
Service Selection ◽  
Context Information ◽  
Context Aware ◽  
Functional Requirements ◽  
Selection Algorithm ◽  
Service Description ◽  
Inexact Matching ◽  
Service Ranking

The current evolution of Service-Oriented Computing in ubiquitous systems is leading to the development of context-aware services. Context-aware services are services of which the description is enriched with context information related to non-functional requirements, describing the service execution environment or its adaptation capabilities. This information is often used for discovery and adaptation purposes. However, in real-life systems, context information is naturally dynamic, uncertain, and incomplete, which represents an important issue when comparing the service description with user requirements. Uncertainty of context information may lead to an inexact match between provided and required service capabilities, and consequently to the non-selection of services. In this chapter, we focus on how to handle uncertain and incomplete context information for service selection. We consider this issue by presenting a service ranking and selection algorithm, inspired by graph-based matching algorithms. This graph-based service selection algorithm compares contextual service descriptions using similarity measures that allow inexact matching. The service description and non-functional requirements are compared using two kinds of similarity measures: local measures, which compare individually required and provided properties, and global measures, which take into account the context description as a whole.

Resolving and Mediating Ambiguous Contexts in Pervasive Environments

2011 ◽  
pp. 122-147 ◽  
Author(s):  
Nirmalya Roy ◽  
Sajal K. Das ◽  
Christine Julien
Keyword(s):  
State Estimation ◽  
Pervasive Computing ◽  
Independent Living ◽  
Vital Signs ◽  
Context Information ◽  
Context Aware ◽  
Information Theoretic ◽  
Significant Challenge ◽  
Environmental Measures ◽  
Optimal State Estimation

Pervasive computing applications envision sensor rich computing and networking environments that can capture various types of contexts of inhabitants of the environment, such as their locations, activities, vital signs, and environmental measures. Such context information is useful in a variety of applications, for example to manage health information to promote independent living in “aging-in-place” scenarios. In reality, both sensed and interpreted contexts are often ambiguous, leading to potentially dangerous decisions if not properly handled. Thus, a significant challenge facing the development of realistic and deployable context-aware services for pervasive computing applications is the ability to deal with these ambiguous contexts. In this chapter, the authors discuss a resource optimized quality assured ontology-driven context mediation framework for resource constrained sensor networks based on efficient context-aware data fusion and information theoretic sensor parameter selection for optimal state estimation. It has the ability to represent contexts according to the applications’ ontology and easily composable ontological rules to mediate ambiguous contexts.

Context-Aware Mobile and Wearable Device Interfaces

2015 ◽  
pp. 308-321
Author(s):  
Claas Ahlrichs ◽  
Hendrik Iben ◽  
Michael Lawo
Keyword(s):  
Interaction Design ◽  
Interface Design ◽  
Wearable Computing ◽  
Wearable Devices ◽  
Future Research ◽  
Context Information ◽  
Context Aware ◽  
Knowledge Based ◽  
Input And Output ◽  
Recent Developments

In this chapter, recent research on context-aware mobile and wearable computing is described. Starting from the observation of recent developments on Smartphones and research done in wearable computing, the focus is on possibilities to unobtrusively support the use of mobile and wearable devices. There is the observation that size and form matters when dealing with these devices; multimodality concerning input and output is important and context information can be used to satisfy the requirement of unobtrusiveness. Here, Frameworks as middleware are a means to an end. Starting with an introduction on wearable computing, recent developments of Frameworks for context-aware user interface design are presented, motivating the need for future research on knowledge-based intuitive interaction design.

Sign in / Sign up

Export Citation Format

Share Document