Novel hybrid pair recommendations based on a large-scale comparative study of concept drift detection

Babüroğlu, Elif Selen; Durmuşoğlu, Alptekin; Dereli, Türkay

doi:10.1016/j.eswa.2020.113786

Cited by 17 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(C3) Adaptability: In practice, the patterns of historical data are no guarantee of future detection accuracy. This is because the distribution of streaming data may show concept drift, i.e., it may be non-stationary (Babüroglu et al, 2021). As such, old patterns need to be updated and new patterns need to be discovered.…”

Section: User-centric Design Principlesmentioning

confidence: 99%

Real-time wildfire detection with semantic explanations

Phan¹,

Quach²,

Nguyen³

et al. 2022

Expert Systems with Applications

View full text Add to dashboard Cite

Section: User-centric Design Principlesmentioning

confidence: 99%

Real-time wildfire detection with semantic explanations

Phan¹,

Quach²,

Nguyen³

et al. 2022

Expert Systems with Applications

View full text Add to dashboard Cite

“…The interests of users or consumers change over time, and new topics may become popular, therefore resulting in interest shift [ 30 ] or concept drift [ 31 ]. Timely add the user’s new purchase information to the model, so as to master the user’s latest preferences, can improve the accuracy of recommendation [ 32 , 33 ]. These two facts emphasize the necessity and importance of model updating where old model retrains on new data.…”

Section: Related Workmentioning

confidence: 99%

Time-Aware Explainable Recommendation via Updating Enabled Online Prediction

Jiang

Zeng

2022

Entropy

View full text Add to dashboard Cite

There has been growing attention on explainable recommendation that is able to provide high-quality results as well as intuitive explanations. However, most existing studies use offline prediction strategies where recommender systems are trained once while used forever, which ignores the dynamic and evolving nature of user–item interactions. There are two main issues with these methods. First, their random dataset split setting will result in data leakage that knowledge should not be known at the time of training is utilized. Second, the dynamic characteristics of user preferences are overlooked, resulting in a model aging issue where the model’s performance degrades along with time. In this paper, we propose an updating enabled online prediction framework for the time-aware explainable recommendation. Specifically, we propose an online prediction scheme to eliminate the data leakage issue and two novel updating strategies to relieve the model aging issue. Moreover, we conduct extensive experiments on four real-world datasets to evaluate the effectiveness of our proposed methods. Compared with the state-of-the-art, our time-aware approach achieves higher accuracy results and more convincing explanations for the entire lifetime of recommendation systems, i.e., both the initial period and the long-term usage.

show abstract

“…Li hai et al [92] suggested substituting a Face RCNN for a Faster RCNN and adding a centre loss that was computed using softmax to improve the classifier's overall performance. In order to overcome the difficulties presented by small objects and various scales in face recognition, baburoglu et al devised a hybrid-resolution model [93] that analyzes photo pyramids in a way that is size-independent and utilizes a scaled hybrid detector. An SSH was created by agghey and colleagues [94] in order to enable multi-scale face recognition by performing detection on feature maps of varying sizes.…”

Section: Cnn Applications For Specialized Object Detectionmentioning

confidence: 99%

An Evaluation of Deep Learning-Based Object Identification

Kolluri

Das

2022

IJRITCC

View full text Add to dashboard Cite

Identification of instances of semantic objects of a particular class, which has been heavily incorporated in people's lives through applications like autonomous driving and security monitoring, is one of the most crucial and challenging areas of computer vision. Recent developments in deep learning networks for detection have improved object detector accuracy. To provide a detailed review of the current state of object detection pipelines, we begin by analyzing the methodologies employed by classical detection models and providing the benchmark datasets used in this study. After that, we'll have a look at the one- and two-stage detectors in detail, before concluding with a summary of several object detection approaches. In addition, we provide a list of both old and new apps. It's not just a single branch of object detection that is examined. Finally, we look at how to utilize various object detection algorithms to create a system that is both efficient and effective. and identify a number of emerging patterns in order to better understand the using the most recent algorithms and doing more study.

show abstract

Novel hybrid pair recommendations based on a large-scale comparative study of concept drift detection

Cited by 17 publications

References 33 publications

Real-time wildfire detection with semantic explanations

Real-time wildfire detection with semantic explanations

Time-Aware Explainable Recommendation via Updating Enabled Online Prediction

An Evaluation of Deep Learning-Based Object Identification

Contact Info

Product

Resources

About