Hybrid Real-Time Matrix Factorization for Implicit Feedback Recommendation Systems

Lin, Chia-Yu; Wang, Li-Chun; Tsai, Kun-Hung

doi:10.1109/access.2018.2819428

Cited by 49 publications

(25 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, none of the previous works have used the latent factor to represent subjects and calculate their similarities. In fact, latent factors from matrix/tensor decomposition are heavily used in recommendation systems to discover users with similar behaviors [39,40]. We apply this idea to our transfer learning framework for BCI to identify similar subjects who exhibit similar brain responses under the same conditions.…”

Section: B Tensor-decomposition-based Model For Learning Subject Repmentioning

confidence: 99%

Low-Dimensional Subject Representation-Based Transfer Learning in EEG Decoding

Jeng

Wei

Jung

et al. 2021

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Recently, the advances in passive brain-computer interfaces (BCIs) based on electroencephalogram (EEG) have shed light on real-world neuromonitoring technologies. However, human variability in the EEG activities hinders the development of practical applications of EEG-based BCI. To tackle this problem, many transfer-learning techniques perform supervised calibration. This kind of calibration approach requires taskrelevant data, which is impractical in real-life scenarios such as drowsiness during driving. This study presents a transferlearning framework for EEG decoding based on the lowdimensional representations of subjects learned from the pre-trial EEG. Tensor decomposition was applied to the pre-trial EEG of subjects to extract the underlying characteristics in subject, spatial and spectral domains. Then, the proposed framework assessed the characteristics to obtain the low-dimensional subject representations such that the subjects with similar brain dynamics can be identified. This method can leverage the existing data from other users and a small number of data from a rapid, nontask, unsupervised calibration from a new user to build an accurate BCI. Our results demonstrated that, in terms of prediction accuracy, the proposed low-dimensional subject representationbased transfer learning (LDSR-TL) framework outperformed the random selection and the Riemannian manifold approach in cognitive-state tracking, while requiring fewer training data. The results can greatly improve the practicability and usability of EEG-based BCI in the real world.

show abstract

Section: B Tensor-decomposition-based Model For Learning Subject Repmentioning

confidence: 99%

Low-Dimensional Subject Representation-Based Transfer Learning in EEG Decoding

Jeng

Wei

Jung

et al. 2021

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, the Interworking Proxy Entity (IPE) was designed to establish the connection of oneM2M, AllJoyn, OCF, and Lightweight M2M in oneM2M's Release 2 [1]. Some communication techniques have been proposed to collect the sensing data and control the devices via different IoT standards and specifications for the applications of agriculture [17][18][19], energy [20,21], enterprise [22,23], finance [24,25], healthcare [26,27], industry [28,29], public services [30,31], residency [32,33], retail [34,35], and transportation [36][37][38][39][40]. Therefore, the aim of this special issue is to introduce to the readers a number of papers on various aspects of IoT applications and techniques.…”

Section: Introductionmentioning

confidence: 99%

Introduction to the Special Issue: Applications of Internet of Things

et al. 2018

View full text Add to dashboard Cite

This editorial introduces the special issue, entitled “Applications of Internet of Things”, of Symmetry. The topics covered in this issue fall under four main parts: (I) communication techniques and applications, (II) data science techniques and applications, (III) smart transportation, and (IV) smart homes. Four papers on sensing techniques and applications are included as follows: (1) “Reliability of improved cooperative communication over wireless sensor networks”, by Chen et al.; (2) “User classification in crowdsourcing-based cooperative spectrum sensing”, by Zhai and Wang; (3) “IoT’s tiny steps towards 5G: Telco’s perspective”, by Cero et al.; and (4) “An Internet of things area coverage analyzer (ITHACA) for complex topographical scenarios”, by Parada et al. One paper on data science techniques and applications is as follows: “Internet of things: a scientometric review”, by Ruiz-Rosero et al. Two papers on smart transportation are as follows: (1) “An Internet of things approach for extracting featured data using an AIS database: an application based on the viewpoint of connected ships”, by He et al.; and (2) “The development of key technologies in applications of vessels connected to the Internet”, by Tian et al. Two papers on smart home are as follows: (1) “A novel approach based on time cluster for activity recognition of daily living in smart homes”, by Liu et al.; and (2) “IoT-based image recognition system for smart home-delivered meal services”, by Tseng et al.

show abstract

“…For sensor and networking layers, the rise of mobile technology advancements [12][13][14][15] (e.g., wireless sensor networking, Wi-Fi, Bluetooth, smart mobile device, and Long Term Evolution (LTE)) has led to a new wave of machine-to-machine (M2M), machine-to-human (M2H), human-to-human (H2H), and human-to-machine (H2M) communications [16][17][18][19][20]. For the application layer, several IoT applications, which include energy [21,22], enterprise [23,24], healthcare [25,26], public services [27,28], residency [29,30], retail [31,32], and transportation [33,34], have been designed and implemented to detect environmental changes and send instant updates to a cloud computing server farm via mobile communications and middleware for big geo-data analyzes [35,36]. For instance, on-board units in cars can instantly detect and share information about the geolocation of the car, speed, following distance, and gaps with other neighboring cars [37][38][39][40].…”

Section: Introductionmentioning

confidence: 99%

Applications of Internet of Things

Chen

2018

IJGI

View full text Add to dashboard Cite

This editorial introduces the special issue entitled “Applications of Internet of Things”, of ISPRS International Journal of Geo-Information. Topics covered in this issue include three main parts: (I) intelligent transportation systems (ITS), (II) location-based services (LBS), and (III) sensing techniques and applications. Three papers on ITS are as follows: (1) “Vehicle positioning and speed estimation based on cellular network signals for urban roads,” by Lai and Kuo; (2) “A method for traffic congestion clustering judgment based on grey relational analysis,” by Zhang et al.; and (3) “Smartphone-based pedestrian’s avoidance behavior recognition towards opportunistic road anomaly detection,” by Ishikawa and Fujinami. Three papers on LBS are as follows: (1) “A high-efficiency method of mobile positioning based on commercial vehicle operation data,” by Chen et al.; (2) “Efficient location privacy-preserving k-anonymity method based on the credible chain,” by Wang et al.; and (3) “Proximity-based asynchronous messaging platform for location-based Internet of things service,” by gon Jo et al. Two papers on sensing techniques and applications are as follows: (1) “Detection of electronic anklet wearers’ groupings throughout telematics monitoring,” by Machado et al.; and (2) “Camera coverage estimation based on multistage grid subdivision,” by Wang et al.

show abstract

Hybrid Real-Time Matrix Factorization for Implicit Feedback Recommendation Systems

Cited by 49 publications

References 21 publications

Low-Dimensional Subject Representation-Based Transfer Learning in EEG Decoding

Low-Dimensional Subject Representation-Based Transfer Learning in EEG Decoding

Introduction to the Special Issue: Applications of Internet of Things

Applications of Internet of Things

Contact Info

Product

Resources

About