User Behavior Data Research Articles

Algorithms For Cold-Start Game Recommendation Based On GNN Pre-training Model

Abstract In the absence of sufficient user behavior data, game recommendation systems face the cold-start problem. To address this issue, this paper proposes a solution based on the Graph Neural Network pre-training model to alleviate the cold-start problem. The proposed model directly reconstructs cold-start user/game embeddings using a meta-learning setup based on dataset training simulations and uses an adaptive neighbor sampler to improve user interaction relations and thereby to improve game recommendation performance. Experimental results demonstrate the effectiveness and practicality of the recommendation model proposed in this study. Moreover, the proposed model is embedded in the game recommendation system to visualize the recommendation results.

Fake User Detection Based on Multi-Model Joint Representation

The existing deep learning-based detection of fake information focuses on the transient detection of news itself. Compared to user category profile mining and detection, transient detection is prone to higher misjudgment rates due to the limitations of insufficient temporal information, posing new challenges to social public opinion monitoring tasks such as fake user detection. This paper proposes a multimodal aggregation portrait model (MAPM) based on multi-model joint representation for social media platforms. It constructs a deep learning-based multimodal fake user detection framework by analyzing user behavior datasets within a time retrospective window. It integrates a pre-trained Domain Large Model to represent user behavior data across multiple modalities, thereby constructing a high-generalization implicit behavior feature spectrum for users. In response to the tendency of existing fake user behavior mining to neglect time-series features, this study introduces an improved network called Sequence Interval Detection Net (SIDN) based on Sequence to Sequence (seq2seq) to characterize time interval sequence behaviors, achieving strong expressive capabilities for detecting fake behaviors within the time window. Ultimately, the amalgamation of latent behavioral features and explicit characteristics serves as the input for spectral clustering in detecting fraudulent users. The experimental results on Weibo real dataset demonstrate that the proposed model outperforms the detection utilizing explicit user features, with an improvement of 27.0% in detection accuracy.

Evaluation of a Microcontroller-based Smart Wearable Device in College Students' Sports Forging Application

INTRODUCTION: The widespread use of smart wearable devices in various fields, including healthcare and sports, underscores the importance of their application in enhancing physical exercise among college students. Recent advancements in technology have facilitated the development of sophisticated methods to assess and predict physical activity outcomes, making their evaluation increasingly critical.OBJECTIVES: This study aims to develop a reliable assessment model for smart wearable devices used in college students' sports activities. The objective is to accurately predict and evaluate the effectiveness of these devices in improving students' physical health and promoting lifelong sports habits. Ultimately, the research seeks to integrate advanced computational methods to enhance the accuracy of physical exercise assessments.METHODS: The research introduces a novel assessment model that combines a zebra behavior-based heuristic optimization algorithm with a convolutional neural network (CNN). By analyzing user behavior data from wearable devices, the model constructs an evaluation index system tailored for college sports activities. The approach optimizes the parameters of the CNN using the zebra optimization algorithm, ensuring enhanced prediction accuracy.RESULTS: The evaluation model demonstrated high accuracy, with a significant improvement in predicting the outcomes of physical exercises among college students. Comparative analyses with traditional methods revealed that the new model reduced prediction errors and increased real-time performance metrics. Specifically, the model achieved a lower root mean square error (RMSE) in simulation tests, indicating more precise assessments. Figures and statistical data provided in the study illustrate the model's superior performance across various parameters.CONCLUSION: The developed assessment model significantly advances the application of smart wearable devices in monitoring and enhancing college students' physical activities. By integrating cutting-edge algorithms, the study not only improves the accuracy of exercise assessments but also contributes to the broader understanding of technology's role in health and fitness education. Future research could further refine this model by incorporating additional sensors and data points to expand its applicability and robustness.

Brand reputation enhancement through data mining in social media

The rise of social media has provided a large range of data such as user behavior data, social relationship data and so on, which can be used for business analysis, and the use of analysis tools can obtain complex, extensive and continuously followed social media data to help enhance the reputation of brand. In this paper, the definition and potential relationship between data analysis, social media and brand reputation and how the analysis results can help enhance business reputation will be introduced. This paper uses the research methodology of review, collecting and analyzing a large amount of literature, and draws a series of effective conclusions, and concludes that data mining of social media can effectively help business analysis to expand brand reputation, indicating that data mining analysis brings a significant improvement in effectiveness of marketing activities[1].

HyperFusion: Combating Phishing Attacks through URL, Hyperlink, and User Behavior Analysis

Abstract: Phishing attacks remain a persistent threat in cyberspace, demanding innovative solutions for timely detection. In this paper, HyperFusion, a pioneering approach that combines machine learning with user behavior analysis, is introduced to enhance the real-time identification of phishing websites. By integrating features derived from URL and hyperlink characteristics with dynamic user interaction patterns, HyperFusion achieves unprecedented accuracy without reliance on thirdparty systems. Traditional anti-phishing methods often falter against zero-hour attacks or novel phishing websites, underscoring the need for novel strategies. The methodology addresses this challenge by leveraging user behavior data alongside client-side information, thereby eliminating external dependencies and fortifying defense mechanisms. Additionally, a tailored dataset for rigorous experimentation is presented, facilitating a comprehensive evaluation of the approach. Experimental results demonstrate HyperFusion's superior efficacy, boasting a remarkable detection accuracy of 99.37% with the XG Boost technique.

Research on Intelligent Analysis Method for the Impact of Running APP Software on Physical Fitness Indicators of College Students

With the development of Internet of Things (IoT) technology, the use of running APP to analyse college students' physical fitness indicators has gradually become a commonly used sports analysis method. Aiming at the problems of insufficient precision of the running APP usage analysis method, easy to fall into the local optimum, and insufficiently comprehensive evaluation effect, this paper proposes a running APP usage analysis method based on deep learning network for some college students' physical fitness indicators. Firstly, feature vectors are taken from the running APP user behaviour data to analyse the values of college students' physical fitness indicators and construct a mapping model of running APP usage analysis for the effects of college students' physical fitness indicators; then, the BiGRU neural network is improved by using the driver-training heuristic optimisation algorithm to construct a running APP usage analysis model for some of the college students' physical fitness indicators; finally, a mapping model is constructed for the effect of running APP usage analysis for some of the college students' physical fitness indicators by using college student-oriented running APP Finally, the effectiveness and robustness of the DTBO algorithm are compared with the user behaviour dataset of the running APP for college students. Finally, the effectiveness and robustness of the DTBO algorithm are compared using the user behaviour data set of the running app platform for college students.

A DQN-based traffic classification method for mobile application recommendation with continual learning

With the popularity and development of smartphones, many mobile applications of various types have emerged. How to recommend mobile applications that match the user’s preferences and usage habits among the massive applications is a problem that needs to be solved. Traditional mobile application recommendation methods cannot dynamically track user behavior and preference changes in time and cannot timely correct the recommendation model, resulting in poor recommendation effects. The continual update of mobile applications will also invalidate the recommendation model based on traffic classification. To solve these problems, this paper proposes A Deep Q-Network (DQN) based traffic classification method for mobile application recommendation with continual learning, which embeds a DQN-based traffic classification model in the mobile terminal and sets up a reward and punishment mechanism to achieve self-supervised learning. By continuously adjusting and optimizing the model, the effectiveness of the traffic classification model is ensured, and the recommendation model is provided with accurate and reliable user behavior data support. Experiments on the ISCX and private datasets show that the proposed method performs better and can effectively guarantee the accuracy of the classification model.

A Security-enhanced Advertising Platform based on Blockchain and Edge Computing in Generative AI

ABSTRACT With the development of advertising technology, especially the emergence of generative artificial intelligence, the generation and editing of advertising content has become more convenient and efficient. However, this also brings new security risks to digital advertising. For example, in order to generate personalized advertising content, AI can collect user behavior data without the user’s knowledge and automatically generate ads that are beneficial to advertisers. In addition, the main issue regarding outdoor advertising is whether the outdoor advertising platform can deliver the advertising content required by the advertiser at the designated place and time according to the actual requirements of the customer. Combining blockchain and edge computing technology, this paper builds a security-enhanced outdoor advertising platform. The decentralized, non-tamperable and traceable features of blockchain technology provide the advertising platform with credibility between users and advertisers, as well as credibility between advertisers and the advertising platform. At the same time, the terminal controller with edge processing capabilities improves the efficiency of advertising and enhances the task balance between the server and the playback side. Experimental results show that the platform can effectively manage user identities and maintain advertising plans. It not only improves data security and credibility, but also has good performance.

Empowering precise advertising with Fed-GANCC: A novel federated learning approach leveraging Generative Adversarial Networks and group clustering.

In the realm of targeted advertising, the demand for precision is paramount, and the traditional centralized machine learning paradigm fails to address this necessity effectively. Two critical challenges persist in the current advertising ecosystem: the data privacy concerns leading to isolated data islands and the complexity in handling non-Independent and Identically Distributed (non-IID) data and concept drift due to the specificity and diversity in user behavior data. Current federated learning frameworks struggle to overcome these hurdles satisfactorily. This paper introduces Fed-GANCC, an innovative federated learning framework that synergizes Generative Adversarial Networks (GANs) and Group Clustering. The framework incorporates a user data augmentation algorithm predicated on adversarial generative networks to enrich user behavior data, curtail the impact of non-uniform data distribution, and enhance the applicability of the global machine learning model. Unlike traditional approaches, our framework offers user data augmentation algorithms based on adversarial generative networks, which not only enriches user behavior data but also reduces the challenges posed by non-uniform data distribution, thereby enhancing the applicability of the global machine learning (ML) model. The effectiveness of Fed-GANCC is distinctly showcased through experimental results, outperforming contemporary methods like FED-AVG and FED-SGD in terms of accuracy, loss value, and receiver operating characteristic (ROC) indicators within the same computing time. Experimental results vindicate the effectiveness of Fed-GANCC, revealing substantial enhancements in accuracy, loss value, and receiver operating characteristic (ROC) metrics compared to FED-AVG and FED-SGD given the same computational time. These outcomes underline Fed-GANCC's exceptional prowess in mitigating issues such as isolated data islands, non-IID data, and concept drift. With its novel approach to addressing the prevailing challenges in targeted advertising such as isolated data islands, non-IID data, and concept drift, the Fed-GANCC framework stands as a benchmark, paving the way for future advancements in federated learning solutions tailored for the advertising domain. The Fed-GANCC framework promises to offer pivotal insights for the future development of efficient and advanced federated learning solutions for targeted advertising.

Application of Sports Equipment Image Intelligent Recognition Response APP in Sports Training and Teaching

INTRODUCTION: The paper addresses the integration of intelligent technology in university physical education, highlighting the need for improved analysis methods for sports equipment image recognition apps to enhance teaching quality.OBJECTIVES: The study aims to develop a more accurate and efficient APP use analysis method for sports equipment image recognition, utilizing intelligent optimization algorithms and kernel limit learning machines.METHODS: The proposed method involves constructing an APP usage effect analysis index system, improving kernel limit learning machines through talent mining algorithms, and validating the model using user behavior data. The method integrates a talent mining algorithm to enhance the kernel limit learning machine (KELM). This integration aims to refine the learning machine’s ability to accurately analyze the large datasets generated by the APP's use, optimizing the parameters to improve prediction accuracy and processing speed.RESULTS: Preliminary tests on the sports equipment image intelligent recognition response APP demonstrate improved accuracy and efficiency in analyzing the APP's usage effects in physical education settings. The study compares the performance of the TDA-KELM algorithm with other algorithms like ELM, KELM, GWO-KELM, SOA-KELM, and AOA-KELM. The TDA-KELM algorithm showed the smallest relative error of 0.025 and a minimal time of 0.0025, indicating higher accuracy and efficiency. The analysis highlighted that the TDA-KELM algorithm outperformed others in analyzing the usage effects of sports equipment image recognition apps, with lower errors and faster processing times.CONCLUSION: The study successfully develops an enhanced APP use analysis method, showcasing potential for more accurate and real-time analysis in the application of sports equipment image recognition in physical education.

Opening the black box of the use phase in circular economy life cycle assessments: Environmental performance of shell jacket reuse

AbstractLife cycle assessment (LCA) is highly needed and widely used to assess the environmental performance of circular economy (CE) measures such as reusing and sharing. However, the results of such LCAs are hampered by limited knowledge about the use phase of consumer products and oversimplification of important use phase aspects such as product functionality, user behavior, displacement, and rebound effects. This paper aims to validate the usefulness of a framework designed to assist practitioners in the generation and utilization of such knowledge in LCAs of circular measures. To validate the framework, a case study is used: reuse of shell jackets enabled by “premium secondhand” stores for outdoor equipment and clothing. The paper demonstrates that conclusions about the environmental performance of reuse can easily be altered depending on the functional unit definition, whether real user behavior data are used, and whether imperfect displacement and rebound effects are considered. For instance, shell jacket life cycles that include reuse and thus may be labeled “circular” have significantly higher environmental impact per use occasion than “linear” ones (used by one principal user the entire lifespan), since “circular” shell jackets are used less frequently, in particular during their first use span. Through facilitating the generation and utilization of environmentally relevant use phase data, which are otherwise often overlooked, the framework seems capable of supporting a better understanding of the environmental performance of CE measures.

Research on Boiler Energy Saving Technology Based on Internet of Things Data

This paper proposes a heat demand prediction model that analyzes the heat behavior of heat users, and analyzes the heat behavior data of heat users through a clustering algorithm to predict their heat demand. This paper is based on the supply-demand balance strategy to reduce the heat loss during the transmission of heat medium, and then improve the energy-saving efficiency of the boiler. The traditional boiler energy-saving and consumption reduction method is to optimize the boiler combustion parameters, improve the fuel combustion efficiency and waste heat recovery technology through the Internet of Things and big data technology. The method of balancing the heat-using end with the load of the boiler at low usage frequency is seldom considered. Therefore, this paper predicts the heat demand of the heat-using end by analyzing its thermal behavior, and balances the heat demand and boiler heat supply under the condition of meeting the heat demand. Finally, through simulation experiments, the validity of the model is verified, and the trend and data can be well predicted in the short-term heat demand prediction.

REVIEWING THE ROLE OF BIG DATA ANALYTICS IN FINANCIAL FRAUD DETECTION

Financial institutions grapple with the escalating nature of fraudulent activities, necessitating innovative and timely detection methods. The review underscores the transformative potential of Big Data Analytics, emphasizing its pivotal role in the ongoing fight against fraud. Delving into the specifics, the paper explores diverse data sources, such as transaction and user behavior data, alongside external data from sources like social media, employing machine learning algorithms and predictive modeling for anomaly detection and risk assessment. Real-time processing emerges as a critical component for swift and effective fraud identification. Critically addressing implementation challenges, including data quality assurance and privacy concerns, the paper showcases case studies of successful Big Data Analytics implementations, highlighting their positive impacts on fraud prevention and financial security. Looking ahead, the review anticipates the role of emerging technologies like blockchain and artificial intelligence in enhancing fraud prevention strategies, emphasizing integration with cybersecurity for robust defense against sophisticated attacks. The paper concludes with recommendations for financial institutions, advocating collaborative efforts and information sharing within the industry. In summary, the review underscores the transformative contributions of Big Data Analytics to financial fraud detection, shaping the future of fraud prevention strategies and fortifying the resilience of the global financial ecosystem..
 Keywords: Big, Data, Analytics, Finance, Fraud, Detection.

Leader in the Digital Entertainment Market: Netflix's Continued Success in a Fiercely Competitive Environment

Leader in the Digital Entertainment Market: Netflix's Continued Success in a Fiercely Competitive Environment

Analysis of web design visual element attention based on user educational background

The evolution of Internet technology has led to an increase in online users. This study focuses on the pivotal role of visual elements in web content conveyance and their impact on user browsing behavior. Therefore, the use of visual elements in web design based on big data has aroused widespread concern among web designers, they apply visual elements to their web design works to make the web more attractive. This study examines the composition and distribution characteristics of key visual elements identified through user behavior data in a big data environment and discusses the use of visual elements in web design in the era of network economy. In addition, this paper issued 200 questionnaires to investigate the degree of attention to visual elements in web pages for users of different occupations and different educational backgrounds. Our survey indicated that visual elements captured the attention of 41% of corporate employees, whereas a mere 1% of social welfare workers focused on web content; 36% of undergraduates pay attention to visual elements of web pages, but only 5% and 4% of postgraduates and doctoral degrees and above. Therefore, the visual elements of the designed web page need to conform to the user's cultural background and professional background.

Privacy-preserving Multi-source Cross-domain Recommendation Based on Knowledge Graph

The cross-domain recommender systems aim to alleviate the data sparsity problem in the target domain by transferring knowledge from the auxiliary domain. However, existing works ignore the fact that the data sparsity problem may also exist in the single auxiliary domain, and sharing user behavior data is restricted by the privacy policy. In addition, their cross-domain models lack interpretability. To address these concerns, we propose a novel multi-source cross-domain model based on knowledge graph. Specifically, to avoid the insufficiency of single auxiliary domain, we construct a knowledge graph comprehensively leveraging items from multiple auxiliary domains. To avoid the leakage of user privacy when user information is transferred to multiple domains, we construct graph for information transfer between items to effectively avoid the propagation of users’ private information between different domains. We implicitly integrate the user–item interaction by transferring the learned item embeddings. To improve the interpretability of cross-domain knowledge transfer, we propose a knowledge graph-based retrieval and fusion method to transfer knowledge derived from multiple auxiliary domains. An attention-based fusion network is designed to enhance the representation of the targeted user and items with the transferred item embedding. We perform extensive experiments on three real-world datasets, demonstrating that our model outperforms the states of the art.

User Behavior Data Mining in Industrial and Individualized Design Based on CAD

User Behavior Data Mining in Industrial and Individualized Design Based on CAD

Self-administered questionnaires enhance emotion estimation of individuals with autism spectrum disorders in a robotic interview setting.

Robots offer many unique opportunities for helping individuals with autism spectrum disorders (ASD). Determining the optimal motion of robots when interacting with individuals with ASD is important for achieving more natural human-robot interactions and for exploiting the full potential of robotic interventions. Most prior studies have used supervised machine learning (ML) of user behavioral data to enable robot perception of affective states (i.e., arousal and valence) and engagement. It has previously been suggested that including personal demographic information in the identification of individuals with ASD is important for developing an automated system to perceive individual affective states and engagement. In this study, we hypothesized that assessing self-administered questionnaire data would contribute to the development of an automated estimation of the affective state and engagement when individuals with ASD are interviewed by an Android robot, which will be linked to implementing long-term interventions and maintaining the motivation of participants. Participants sat across a table from an android robot that played the role of the interviewer. Each participant underwent a mock job interview. Twenty-five participants with ASD (males 22, females 3, average chronological age = 22.8, average IQ = 94.04) completed the experiment. We collected multimodal data (i.e., audio, motion, gaze, and self-administered questionnaire data) to train a model to correctly classify the state of individuals with ASD when interviewed by an android robot. We demonstrated the technical feasibility of using ML to enable robot perception of affect and engagement of individuals with ASD based on multimodal data. For arousal and engagement, the area under the curve (AUC) values of the model estimates and expert coding were relatively high. Overall, the AUC values of arousal, valence, and engagement were improved by including self-administered questionnaire data in the classification. These findings support the hypothesis that assessing self-administered questionnaire data contributes to the development of an automated estimation of an individual's affective state and engagement. Given the efficacy of including self-administered questionnaire data, future studies should confirm the effectiveness of such long-term intervention with a robot to maintain participants' motivation based on the proposed method of emotion estimation.

A Debiasing Autoencoder for Recommender System

The deep neural network (DNN)-based recommender system (RS) has drawn much attention recently and provided state-of-the-art results. Although many DNN-based RSs have been achieved, most focus on inventing a sophisticated DNN with a single-metric loss function to fit user behavior data. However, user behavior data are commonly collected from numerous users in complex scenarios, making various biases and outliers (outliers can be seen as the special bias) widely exist in the data. Unfortunately, prior DNN-based RSs only considered rather fragmented biases and lacked a comprehensive solution. To fill this gap, this paper proposes an AutoRec++ model to comprehensively address the various biases existed in user behavior data. Its main idea is to employ different combinations of preprocessing bias (PB) and training bias (TB) as well as L1-norm and L2-norm to form a multi-metric loss function-oriented Autoencoder. As such, AutoRec++ possesses the multi-merits of the PB’s and TB’s debiasing ability, the L1-norm’s robustness, and the L2-norm’s stability. By conducting extensive experiments on five benchmark datasets, we demonstrate that: 1) the incorporation of PB and TB can significantly boost Autoencoder’s prediction accuracy and computational efficiency without structural change, and 2) our AutoRec++ achieves better prediction accuracy and robustness than both DNN-based and non-DNN-based state-of-the-art models. Besides, our AutoRec++ is more effective in processing sparser user behavior data. Our code is available at the link: https://github.com/wudi1989/AutoRec_Plus.

Sequence recommendation algorithm fusing filter and transformer under joint training

In existing sequential recommendation systems, user behavior data are directly used as training data for the model to complete the training process and address recommendation tasks. However, user-generated behavioral data inevitably contains noise, and the use of the Transformer’s recommendation model may lead to overfitting on such noisy data. To address this issue, we introduce a sequence recommendation algorithm model named FAT-Rec, which incorporates fusion filters and converters through joint training. By employing joint training methods, we establish both a transformer prediction layer and a CTR prediction layer. Toward the end of the model, we assign weights and sum up the losses from the Transformer and CTR prediction layers to derive the final loss function. Experimental results on two widely used datasets, MovieLens and Goodbooks, demonstrate a significant enhancement in the performance of the proposed FAT-Rec recommendation algorithm compared with seven comparative models. This validates the efficacy of the fusion filter and transformer within the context of sequence recommendation tasks under the joint training mechanism.