A5070055083- Recommender Systems and Techniques
- Privacy-Preserving Technologies in Data
- Human Mobility and Location-Based Analysis
- Data Management and Algorithms
- Cryptography and Data Security
- Caching and Content Delivery
- Traffic Prediction and Management Techniques
- Advanced Graph Neural Networks
- Digital Marketing and Social Media
- Advanced Clustering Algorithms Research
- Face and Expression Recognition
- Privacy, Security, and Data Protection
- Video Surveillance and Tracking Methods
- Sentiment Analysis and Opinion Mining
- Complex Network Analysis Techniques
- Internet Traffic Analysis and Secure E-voting
- Imbalanced Data Classification Techniques
- Anomaly Detection Techniques and Applications
- Image and Video Quality Assessment
- Cloud Data Security Solutions
- Web Data Mining and Analysis
- Transportation Planning and Optimization
- Network Security and Intrusion Detection
- Advanced Technologies in Various Fields
- Peer-to-Peer Network Technologies
Anhui Normal University
2016-2025
Anhui Institute of Information Technology
2018-2024
Huaibei Normal University
2023
Ningbo University
2009
In recent years, the number of review texts on online travel sites has increased dramatically, which provided a novel source data for research. Sentiment analysis is process that can extract tourists’ sentiments regarding destinations from texts. The results sentiment form an important basis tourism decision making. Thus far, there been minimal concern as to how methods be effectively applied improve effect analysis. However, are largely short characterized by uneven distribution, makes it...
Tourism route planning is widely applied in the smart tourism field. The Pareto-optimal front obtained by traditional multi-objective evolutionary algorithm exhibits long tails, sharp peaks and disconnected regions problems, which leads to uneven distribution weak diversity of optimization solutions routes. Inspired these limitations, we propose a for recommendation (MOTRR) with two-stage Pareto layering based on decomposition. method decomposes problem into several subproblems, improves...
The recommendation system (RS) predicts user ratings by collecting information, but the users' private information may be exposed in this process. Thus, it is crucial to achieving a balance between performance and privacy-preserving of RSs. Aiming solve above problem, article proposes novel matrix factorization (MF) algorithm. algorithm rating through linear weighting global average rating, item MF, which improves prediction accuracy. Then, based on algorithm, MF RS for preserving privacy...
Compared with traditional recommendation algorithms based on collaborative filtering and content, the sequential can better capture changes in user interests recommend items that may be interacted by next time according to user's historical interaction behaviors. Generally, there are several methods for recommendation: Markov Chain (MC) Deep Neutral Network (DNN), both of which ignore relationship between various behaviors dynamic interest over time. Furthermore, early research usually deal...
Indoor object recognition is a key task for indoor navigation by mobile robots. Although previous work has produced impressive results in recognizing known and familiar objects, the research of robot still insufficient. In order to improve detection precision, our study proposed prior knowledge-based deep learning method aimed enable recognize objects on sight. First, we integrate public dataset private frames videos (FoVs) train convolutional neural network (CNN). Second, mean images, which...
With the advent and popularity of e-commerce, an increasing number consumers prefer to order tourism products online. A recommender system can help these users contend with information overload; however, such a is affected by cold start problem. Online destination searching more difficult task than others on account its restrictive factors. In this paper, we therefore propose that employs opinion-mining technology refine user preferences item opinion reputations. These elements are then...
Density peaks clustering is a novel and efficient density-based algorithm. However, the problem of sensitive information leakage associated security risk with applications methods rarely considered. To address problem, we proposed differential privacy-preserving density peaks' based on shared near neighbors similarity method in this paper. First, Euclidean distance were combined to define local sample, Laplace noise was added shortest protect privacy. Second, process cluster center selection...
Recommender system can efficiently alleviate the information overload problem, but it has been trapped in recommendation accuracy. We proposed a new recommender which based on matrix factorization techniques. More factors including contextual information, user ratings and item feature are all taken into consideration. Meanwhile k-modes algorithm is used to reduce complexity of operations increase relevance user-item sub-matrix. Compared with several major existing approaches, extensive...
Nowadays, people choose to travel in their leisure time more frequently, but fixed predetermined tour routes can barely meet people’s personalized preferences. The needs of tourists are diverse, largely personal, and possibly have multiple constraints. traditional single-objective route planning algorithm struggles effectively deal with such problems. In this paper, a novel multi-objective multi-constraint recommendation method is proposed. Firstly, ArcMap was used model the actual road...
Technological advances have led to numerous developments in data sources. Geo-tagged photo metadata has provided a new source of mass research for tourism studies. A series processing methods centering on the various types information contained geo-tagged thus been proposed; as result, development studies based such advanced. However, an in-depth study designed conduct tourist flow prediction not yet conducted. In order acquire accurate substitutive regarding inbound flows cities, this paper...
The results of road congestion detection can be used for the rational planning travel routes and as guidance traffic management. trajectory data moving objects record their positions at each moment reflect features. Utilizing mining technology to effectively identify locations is great importance has practical value in fields urban planning. This paper addresses issue by proposing a novel approach detect based on stay-place clustering. First, this estimates speed status time-stamped location...
How to efficiently collect sensory data for supporting energy-efficient operation of buildings has become a great challenge, especially large-scale networks in buildings. In this paper, spatiotemporal compression-based optimized clustering scheme is proposed environmental collection the scheme, first, according establishment cluster, an adaptive dynamic cluster head selection method prolonging lifetime nodes developed. Meanwhile, further reduce energy consumption, we construct optimal...