International Journal of Web Engineering and Technology (7 papers in press)

Regular Issues

• Service Recommendation Method based on Text View and Interaction View  
  by Shuaijia Lin, Ting Yu, Yaqi Wang, Jie Xu, Fangying Cheng, Tian Liang 
  Abstract: With the increasing prosperity of web service-sharing platforms, more and more software developers are reusing web services when developing applications. Existing web service recommendation systems often face two challenges. Firstly, developers discover services by inputting requirements, but the user's input is arbitrary and it cannot fully reflect the user's intention. Secondly, the application-service interaction records are too sparse, making it particularly difficult to find services that meet the requirements. To address the above challenges, in this paper, we propose a service recommendation method based on text and interaction views (SRTI). Firstly, SRTI employs graph neural network to deeply mine the features of applications and services. Secondly, SRT uses transformer and fully connected neural networks to deeply mine the matching degree between candidate services and requirements. Finally, we integrate the above two to obtain the final service list. Extensive experiments on real-world datasets have shown that SRTI outperforms several state-of-the-art methods.
  Keywords: service recommendation; text view; interaction view; application; recommendation algorithm.
  DOI: 10.1504/IJWET.2024.10064249
   
  
• Practice of College Music Intangible Cultural Heritage Based on Clustering Improved Distance Beat Tracking Algorithm  
  by Xiaolei Liu 
  Abstract: The survival, inheritance, and development of intangible cultural heritage of music face serious challenges. Traditional point-to-point inheritance has limitations and is likely to lead to cultural loss. It is crucial to introduce music intangible cultural heritage into university classrooms and innovate music creation forms based on youth groups. The study employs pulse coding modulation encoding and end-point intensity curve extraction to achieve beat tracking through a maximum and minimum distance clustering method of BPM features in signal time and frequency domain analysis. An improved musical beat tracking model is created based on clustering. Experimental results showed that the model accurately tracked the musical beat (average P-Score = 61.719, Cemgil = 48.640, CMLc = 20.174, AML t = 49.862). This research model is significant for protecting music intangible cultural heritage. This study explores the practical application of the distance beat tracking algorithm based on cluster improvement to introduce music intangible cultural heritage into college classes. The study provides effective methods and ideas for the inheritance and protection of music intangible cultural heritage, and contributes to the innovation of teaching modes in college music classes. The findings have significant implications for the protection of music intangible cultural heritage.
  Keywords: protection of intangible cultural heritage; BPM; clustering method; music class.
  DOI: 10.1504/IJWET.2024.10064806
   
  
• A Cluster-based Approach for Distributed Anonymization of Vertically Partitioned Data  
  by Antonios Xenakis, Z. Chen, George Karabatis 
  Abstract: In modern organisations, data is often spread across different sites, posing challenges for effective analysis. Transferring data to a centralised server may jeopardise privacy and leak sensitive/proprietary information. Therefore, organisations hesitate adopting this solution despite its potential to fully utilise, and analyse the data, for better decision making. Current approaches concentrate on distributed privacy-preserving techniques for data analysis, where data does not leave each site, but incurs substantial computational and communication overhead. This paper focuses on distributed data that is anonymised on site, then merged and sent to a centralised server for analysis. Two new approaches on cluster-based distributed anonymisation are introduced for vertically partitioned data, one based on distributed coordinated anonymisation, and the other based on top-down distributed anonymisation, resulting in low initial onsite anonymisation overhead. Experiments show these approaches preserve data privacy with very minor loss of utility of anonymised data and impose minimal computational overhead.
  Keywords: privacy; distributed anonymisation; differential privacy; K-anonymity; cluster-based anonymisation.
  DOI: 10.1504/IJWET.2024.10064904
   
  
• Identification of Badminton Players' Swinging Movements Based on Improved Dense Trajectory Algorithm  
  by Xue Jiang 
  Abstract: Badminton, as a fast and highly technical sport, requires high accuracy in identifying athletes' swing movements. Accurately identifying different swing movements is of great significance for technical analysis, coach guidance, and game evaluation. To improve the recognition accuracy of badminton players' swing movements, this text is based on an improved dense trajectory algorithm to improve the accuracy of recognising badminton players' swing movements. The features are efficiently extracted and encoded. The results on the KTH, UCF Sports, and Hollywood2 datasets demonstrated that the improved algorithm achieved recognition accuracy of 94.2%, 88.2%, and 58.3%, respectively. Compared to traditional methods, the innovation of research lies in optimised feature extraction methods, efficient algorithm design, and accurate action recognition. These results provide new ideas for the research and application of badminton swing motion recognition.
  Keywords: badminton; swing recognition; dense trajectories; feature extraction; algorithm optimisation.
  DOI: 10.1504/IJWET.2024.10065586
   
  
• Why provenance of SPARQL 1.1 queries  
  by Anastasia Analyti 
  Abstract: In this paper, we study and provide algorithms for source why provenance of answers of extended SPARQL queries Extended SPARQL queries are an extension of SPARQL 1 1 queries which support not only a single dataset but multiple datasets, each in a particular context For example, normal subqueries, aggregate subqueries, (NOT) EXISTS filter subqueries may (optionally) have their own dataset Additionally, GRAPH patterns can query multiple RDF graphs from the local FROM NAMED dataset and not just one For monotonic queries, the source why provenance sets that we derive for an answer mapping are each the minimal set of sources that if we consider as they are while the rest of the sources are considered empty, we derive the same mapping We show that this property does not hold for non-monotonic queries. Among others, knowing source why provenance is of critical importance for judging confidence on the answer, allow information quality assessment, accountability, as well as understanding the temporal and spatial status of information.
  Keywords: extended SPARQL queries; query pattern source why sets; source why provenance; algorithms.
  DOI: 10.1504/IJWET.2024.10065589
   
  
• Synoptic Crow Search with Recurrent Transformer Network for DDoS Attack Detection in IoT-based Smart Homes  
  by Abhijeet R. Raipurkar  
  Abstract: Smart home devices are vulnerable to various attacks, including distributed-denial-of-service (DDoS) attacks. Current detection techniques face challenges due to nonlinear thought, unusual system traffic, and the fluctuating data flow caused by human activities and device interactions. Identifying the baseline for normal traffic and suspicious activities like DDoS attacks from encrypted data is also challenging due to the encrypted protective layer. This work introduces a concept called synoptic crow search with recurrent transformer network-based DDoS attack detection, which uses the synoptic weighted crow search algorithm to capture varying traffic patterns and prioritise critical information handling. An adaptive recurrent transformer neural network is introduced to effectively regulate DDoS attacks within encrypted data, counting the historical context of the data flow. The proposed model shows effective performance in terms of low false alarm rate, higher detection rate, and accuracy.
  Keywords: smart homes; internet of things; network security; distributed denial of service; attack detection; crow search algorithm; CSA; recurrent neural network.
  DOI: 10.1504/IJWET.2024.10065590
   
  
• Using the SCRM Method to Repair a Damaged Planning Graph for Service Composition  
  by Zhihao Gao, Ming Zhu, Jing Li, Rui Lu 
  Abstract: Software, hardware, data, and computing power can be abstracted and encapsulated as services authorised to users in a paid or free manner for on demand deployment. Service composition combines multiple existing services in a certain logical order to solve complex tasks that a single service cannot complete. Many AI approaches have been proposed to solve service composition problems. However, the network environment is dynamic, and services in a composition may disappear or change. Furthermore, the composition requirement of a user may also vary. The composition plan should adjust accordingly. This paper proposes a repairing service composition approach based on a planning graph. We repair a solution from the last layer, then search backward for missing services. Return a repaired solution until a satisfactory result is obtained. To verify the effectiveness and efficiency of our approach, experiments are carried out compared with some repair methods and replanning approaches. Experimental results indicate that our approach has an average 5.05% higher chance of finding a solution compared to the original repair method.
  Keywords: planning graph; repair service composition; web service.
  DOI: 10.1504/IJWET.2024.10065591