A5100440215- Recommender Systems and Techniques
- Topic Modeling
- Advanced Graph Neural Networks
- Multimodal Machine Learning Applications
- Digital Marketing and Social Media
- Customer churn and segmentation
- Human Mobility and Location-Based Analysis
- Web Data Mining and Analysis
- Data Mining Algorithms and Applications
- Advanced Computational Techniques and Applications
- Caching and Content Delivery
- Image and Video Quality Assessment
- Advanced Image and Video Retrieval Techniques
- Blockchain Technology Applications and Security
- Stock Market Forecasting Methods
- Advanced Algorithms and Applications
- Cloud Computing and Resource Management
- Advanced Text Analysis Techniques
- scientometrics and bibliometrics research
- Currency Recognition and Detection
- Blasting Impact and Analysis
- ICT in Developing Communities
- Advanced Computing and Algorithms
- Data Stream Mining Techniques
- Online Learning and Analytics
University of Glasgow
2023-2025
Dalian Maritime University
2023-2025
Amazon (United States)
2024
Telefonica Research and Development
2024
Shandong University
2024
University of Massachusetts Lowell
2015-2024
Westlake University
2024
Soochow University
2022-2023
Guangdong Open University
2023
Changchun University
2022-2023
Adapters, a plug-in neural network module with some tunable parameters, have emerged as parameter-efficient transfer learning technique for adapting pre-trained models to downstream tasks, especially natural language processing (NLP) and computer vision (CV) fields. Meanwhile, recommendation directly from raw item modality features --- e.g., texts of NLP images CV can enable effective transferable recommender systems (called TransRec). In view this, question arises:can adapter-based...
This study provides the game-theoretical framework to investigate relationship between blockchain service and mass customization in environment of information sharing contract coordination. Specifically, we construct models manufacturer retailer discuss optimal strategy by case customization. The result explores conditions for because she understands end market nearby consumers. discussion helps us understand that motivation pays retailer’s construction a system two types products, such as...
Discriminative pattern mining is one of the most important techniques in data mining. This challenging task concerned with finding a set patterns that occur disproportionate frequency sets various class labels. Such are great value for group difference detection and classifier construction. Research on interesting discriminative class-labeled evolves rapidly lots algorithms have been proposed to specifically address this problem. proven their considerable biological analysis. The...
Bitcoin is one of the most successful cryptocurrencies, and research on price predictions receiving more attention. To predict fluctuations better effectively, it necessary to establish a abundant index system prediction model with effect. In this study, combined twin support vector regression was used as main model. Twenty-seven factors related prices were collected. Some that have greatest impact selected by using XGBoost algorithm random forest algorithm. The (SVR), least-squares (LSSVR),...
Large foundational models, through upstream pre-training and downstream fine-tuning, have achieved immense success in the broad AI community due to improved model performance significant reductions repetitive engineering. By contrast, <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">trans</u> ferable one-for-all models xmlns:xlink="http://www.w3.org/1999/xlink">rec</u> ommender system field, referred as TransRec, made limited progress. The...
Image-text matching (ITM) is a fundamental problem in computer vision. The key issue lies jointly learning the visual and textual representation to estimate their similarity accurately. Most existing methods focus on feature enhancement within modality or interaction across modalities, which, however, neglects contextual information of object based inter-object relationships that match corresponding sentences with rich semantics. In this paper, we propose Hybrid-modal Interaction multiple...
As service computing becomes increasingly prevalent, the number of web services grows rapidly. It very important to recommend suitable, personalized users. Collaborative Filtering based on Quality Service (QoS) has been widely used for recommendation, and variety factors such as location, environment are taken into account improve accuracy recommendation. However, temporal influences, which is one key affecting QoS, not fully considered by investigators. In this paper, we propose a novel...
Tourism is both an important industry and popular leisure activity undertaken by millions around the world. How to effectively mine user's travel mode visit preferences based on historical data a challenge. The tourism resources of different visiting areas, such as popularity POI (Point Interest), influence interests dynamically. Therefore, interest during traveling may differ between geographical region. In this paper, we introduce personalized route recommendation framework, named PTDR,...
Online shopping has become increasingly popular in recent years. More and more people are willing to buy products through Internet instead of physical stores. For promotional purposes, almost all online merchants provide product recommendations their returning customers. Some them ask professional recommendation service providers help develop maintain recommender systems while others need share data with similar shops for better recommendations. There two issues, (1) how protect customers’...
Social media has emerged as a widespread phenomenon, with numerous users engaging in observing, creating, and distributing content. The growing content led to user conflicts, encompassing bullying, aggression, harassment, threats. Consequently, recent research aimed identify address these openly hostile forms of social conflict. However, the less overtly yet equally damaging types conflict, including teasing, criticism, sarcasm, have been overlooked current studies.
In recent years, due to an increasing overload of information on the Internet, there are many scenarios where Recommender Systems (RSs) employed provide suggestions user groups. However, most proposed approaches group recommendations simply aggregate individual ratings or prediction results, rather than comprehensively investigating hidden correlative between members and group, which results in inferior recommendation performance. this paper, we propose a new approach, RWR-UTM, for based...
Natural products play an important role in drug development and lead compound synthesis. Neocryptolepine is a polycyclic quinoline isolated from Cryptolepis sanguinolent. The cytotoxicity of neocryptolepine to gastric cancer cells AGS, MKN45, HGC27, SGC7901 was not very strong, it also had certain toxicity mucosa GES-1. Therefore, series derivatives were synthesized by the modification structure neocryptolepine, their evaluated. results showed that compounds C5 C8 exhibited strong AGS cells....
The characterization and bioactive properties of carotenoid produced by Gordonia rubripertincta GH-1 originating from Pixian Douban (PXDB), the Chinese traditional condiment, was investigated. purified yellow pigment characterized ultraviolet-visible spectroscopy (UV-Vis), Fourier transformed infrared (FTIR), nuclear magnetic resonance (NMR), high-resolution mass spectrometry (HRMS), identified as lutein. Additionally, activity lutein G. evaluated measuring free radical scavenging capacity...
Bitcoin is one of the most successful cryptocurrencies, and research on price prediction getting more attention. Previous studies have used traditional statistical methods machine learning models to predict prices. However, previous also many problems, such as too few influencing factors, lack model optimization, poor effect. This paper selects 27 factors related changes screens features through XGBoost algorithm Random Forest (RF). In this study, combined forecasting based Support Vector...