International Journal of Web Information Systems最新文献

{"title":"Web-aided data set expansion in deep learning: evaluating trainable activation functions in ResNet for improved image classification","authors":"Zhiqiang Zhang, Xiaoming Li, Xinyi Xu, Chengjie Lu, Yihe Yang, Zhiyong Shi","doi":"10.1108/ijwis-05-2024-0135","DOIUrl":"https://doi.org/10.1108/ijwis-05-2024-0135","url":null,"abstract":"\u0000Purpose\u0000The purpose of this study is to explore the potential of trainable activation functions to enhance the performance of deep neural networks, specifically ResNet architectures, in the task of image classification. By introducing activation functions that adapt during training, the authors aim to determine whether such flexibility can lead to improved learning outcomes and generalization capabilities compared to static activation functions like ReLU. This research seeks to provide insights into how dynamic nonlinearities might influence deep learning models' efficiency and accuracy in handling complex image data sets.\u0000\u0000\u0000Design/methodology/approach\u0000This research integrates three novel trainable activation functions – CosLU, DELU and ReLUN – into various ResNet-n architectures, where “n” denotes the number of convolutional layers. Using CIFAR-10 and CIFAR-100 data sets, the authors conducted a comparative study to assess the impact of these functions on image classification accuracy. The approach included modifying the traditional ResNet models by replacing their static activation functions with the trainable variants, allowing for dynamic adaptation during training. The performance was evaluated based on accuracy metrics and loss profiles across different network depths.\u0000\u0000\u0000Findings\u0000The findings indicate that trainable activation functions, particularly CosLU, can significantly enhance the performance of deep learning models, outperforming the traditional ReLU in deeper network configurations on the CIFAR-10 data set. CosLU showed the highest improvement in accuracy, whereas DELU and ReLUN offered varying levels of performance enhancements. These functions also demonstrated potential in reducing overfitting and improving model generalization across more complex data sets like CIFAR-100, suggesting that the adaptability of activation functions plays a crucial role in the training dynamics of deep neural networks.\u0000\u0000\u0000Originality/value\u0000This study contributes to the field of deep learning by introducing and evaluating the impact of three novel trainable activation functions within widely used ResNet architectures. Unlike previous works that primarily focused on static activation functions, this research demonstrates that incorporating trainable nonlinearities can lead to significant improvements in model performance and adaptability. The introduction of CosLU, DELU and ReLUN provides a new pathway for enhancing the flexibility and efficiency of neural networks, potentially setting a new standard for future deep learning applications in image classification and beyond.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141654912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Click-through rate prediction model based on graph networks and feature squeeze-and-excitation mechanism","authors":"Zhongqin Bi, Susu Sun, Weina Zhang, Meijing Shan","doi":"10.1108/ijwis-07-2023-0110","DOIUrl":"https://doi.org/10.1108/ijwis-07-2023-0110","url":null,"abstract":"\u0000Purpose\u0000Predicting a user’s click-through rate on an advertisement or item often uses deep learning methods to mine hidden information in data features, which can provide users with more accurate personalized recommendations. However, existing works usually ignore the problem that the drift of user interests may lead to the generation of new features when they compute feature interactions. Based on this, this paper aims to design a model to address this issue.\u0000\u0000\u0000Design/methodology/approach\u0000First, the authors use graph neural networks to model users’ interest relationships, using the existing user features as the node features of the graph neural networks. Second, through the squeeze-and-excitation network mechanism, the user features and item features are subjected to squeeze operation and excitation operation, respectively, and the importance of the features is adaptively adjusted by learning the channel weights of the features. Finally, the feature space is divided into multiple subspaces to allocate features to different models, which can improve the performance of the model.\u0000\u0000\u0000Findings\u0000The authors conduct experiments on two real-world data sets, and the results show that the model can effectively improve the prediction accuracy of advertisement or item click events.\u0000\u0000\u0000Originality/value\u0000In the study, the authors propose graph network and feature squeeze-and-excitation model for click-through rate prediction, which is used to dynamically learn the importance of features. The results indicate the effectiveness of the model.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141665073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing the viewing, browsing and searching of knowledge graphs with virtual properties","authors":"Henrik Dibowski","doi":"10.1108/ijwis-02-2023-0027","DOIUrl":"https://doi.org/10.1108/ijwis-02-2023-0027","url":null,"abstract":"\u0000Purpose\u0000Adequate means for easily viewing, browsing and searching knowledge graphs (KGs) are a crucial, still limiting factor. Therefore, this paper aims to present virtual properties as valuable user interface (UI) concept for ontologies and KGs able to improve these issues. Virtual properties provide shortcuts on a KG that can enrich the scope of a class with other information beyond its direct neighborhood.\u0000\u0000\u0000Design/methodology/approach\u0000Virtual properties can be defined as enhancements of shapes constraint language (SHACL) property shapes. Their values are computed on demand via protocol and RDF query language (SPARQL) queries. An approach is demonstrated that can help to identify suitable virtual property candidates. Virtual properties can be realized as integral functionality of generic, frame-based UIs, which can automatically provide views and masks for viewing and searching a KG.\u0000\u0000\u0000Findings\u0000The virtual property approach has been implemented at Bosch and is usable by more than 100,000 Bosch employees in a productive deployment, which proves the maturity and relevance of the approach for Bosch. It has successfully been demonstrated that virtual properties can significantly improve KG UIs by enriching the scope of a class with information beyond its direct neighborhood.\u0000\u0000\u0000Originality/value\u0000SHACL-defined virtual properties and their automatic identification are a novel concept. To the best of the author’s knowledge, no such approach has been established nor standardized so far.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140698454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GethReplayer: a smart contract testing method based on transaction replay","authors":"Xiaohong Shi, Ziyan Wang, Runlu Zhong, Liangliang Ma, Xiangping Chen, Peng Yang","doi":"10.1108/ijwis-08-2023-0138","DOIUrl":"https://doi.org/10.1108/ijwis-08-2023-0138","url":null,"abstract":"\u0000Purpose\u0000Smart contracts are written in high-level programming languages, compiled into Ethereum Virtual Machine (EVM) bytecode, deployed onto blockchain systems and called with the corresponding address by transactions. The deployed smart contracts are immutable, even if there are bugs or vulnerabilities. Therefore, it is critical to verify smart contracts before deployment. This paper aims to help developers effectively and efficiently locate potential defects in smart contracts.\u0000\u0000\u0000Design/methodology/approach\u0000GethReplayer, a smart contract testing method based on transaction replay, is proposed. It constructs a parallel transaction execution environment with two virtual machines to compare the execution results. It uses the real existing transaction data on Ethereum and the source code of the tested smart contacts as inputs, conditionally substitutes the bytecode of the tested smart contract input into the testing EVM, and then monitors the environmental information to check the correctness of the contract.\u0000\u0000\u0000Findings\u0000Experiments verified that the proposed method is effective in smart contract testing. Virtual environmental information has a significant effect on the success of transaction replay, which is the basis for the performance of the method. The efficiency of error locating was approximately 14 times faster with the proposed method than without. In addition, the proposed method supports gas consumption analysis.\u0000\u0000\u0000Originality/value\u0000This paper addresses the difficulty that developers encounter in testing smart contracts before deployment and focuses on helping develop smart contracts with as few defects as possible. GethReplayer is expected to be an alternative solution for smart contract testing and provide inspiration for further research.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140737656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Web-enhanced unmanned aerial vehicle target search method combining imitation learning and reinforcement learning","authors":"Tao Pang, Wenwen Xiao, Yilin Liu, Tao Wang, Jie Liu, Mingke Gao","doi":"10.1108/ijwis-10-2023-0186","DOIUrl":"https://doi.org/10.1108/ijwis-10-2023-0186","url":null,"abstract":"Purpose\u0000This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the limitations of expert demonstration data and reduces the dimensionality of the agent’s exploration space to speed up the training convergence rate.\u0000\u0000Design/methodology/approach\u0000Firstly, the decay weight function is set in the objective function of the agent’s training to combine both types of methods, and both RL and imitation learning (IL) are considered to guide the agent's behavior when updating the policy. Second, this study designs a coupling utilization method between the demonstration trajectory and the training experience, so that samples from both aspects can be combined during the agent’s learning process, and the utilization rate of the data and the agent’s learning speed can be improved.\u0000\u0000Findings\u0000The method is superior to other algorithms in terms of convergence speed and decision stability, avoiding training from scratch for reward values, and breaking through the restrictions brought by demonstration data.\u0000\u0000Originality/value\u0000The agent can adapt to dynamic scenes through exploration and trial-and-error mechanisms based on the experience of demonstrating trajectories. The demonstration data set used in IL and the experience samples obtained in the process of RL are coupled and used to improve the data utilization efficiency and the generalization ability of the agent.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140357147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large language models for automated Q&A involving legal documents: a survey on algorithms, frameworks and applications","authors":"Xiaoxian Yang, Zhifeng Wang, Qi Wang, Ke Wei, Kaiqi Zhang, Jiangang Shi","doi":"10.1108/ijwis-12-2023-0256","DOIUrl":"https://doi.org/10.1108/ijwis-12-2023-0256","url":null,"abstract":"Purpose\u0000This study aims to adopt a systematic review approach to examine the existing literature on law and LLMs.It involves analyzing and synthesizing relevant research papers, reports and scholarly articles that discuss the use of LLMs in the legal domain. The review encompasses various aspects, including an analysis of LLMs, legal natural language processing (NLP), model tuning techniques, data processing strategies and frameworks for addressing the challenges associated with legal question-and-answer (Q&A) systems. Additionally, the study explores potential applications and services that can benefit from the integration of LLMs in the field of intelligent justice.\u0000\u0000Design/methodology/approach\u0000This paper surveys the state-of-the-art research on law LLMs and their application in the field of intelligent justice. The study aims to identify the challenges associated with developing Q&A systems based on LLMs and explores potential directions for future research and development. The ultimate goal is to contribute to the advancement of intelligent justice by effectively leveraging LLMs.\u0000\u0000Findings\u0000To effectively apply a law LLM, systematic research on LLM, legal NLP and model adjustment technology is required.\u0000\u0000Originality/value\u0000This study contributes to the field of intelligent justice by providing a comprehensive review of the current state of research on law LLMs.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140355088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PDMSC: privacy-preserving decentralized multi-skill spatial crowdsourcing","authors":"Zhaobin Meng, Yueheng Lu, Hongyue Duan","doi":"10.1108/ijwis-09-2023-0143","DOIUrl":"https://doi.org/10.1108/ijwis-09-2023-0143","url":null,"abstract":"Purpose\u0000The purpose of this paper is to study the following two issues regarding blockchain crowdsourcing. First, to design smart contracts with lower consumption to meet the needs of blockchain crowdsourcing services and also need to design better interaction modes to further reduce the cost of blockchain crowdsourcing services. Second, to design an effective privacy protection mechanism to protect user privacy while still providing high-quality crowdsourcing services for location-sensitive multiskilled mobile space crowdsourcing scenarios and blockchain exposure issues.\u0000\u0000Design/methodology/approach\u0000This paper proposes a blockchain-based privacy-preserving crowdsourcing model for multiskill mobile spaces. The model in this paper uses the zero-knowledge proof method to make the requester believe that the user is within a certain location without the user providing specific location information, thereby protecting the user’s location information and other privacy. In addition, through off-chain calculation and on-chain verification methods, gas consumption is also optimized.\u0000\u0000Findings\u0000This study deployed the model on Ethereum for testing. This study found that the privacy protection is feasible and the gas optimization is obvious.\u0000\u0000Originality/value\u0000This study designed a mobile space crowdsourcing based on a zero-knowledge proof privacy protection mechanism and optimized gas consumption.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140223335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Web intelligence-enhanced unmanned aerial vehicle target search model based on reinforcement learning for cooperative tasks","authors":"Mingke Gao, Zhenyu Zhang, Jinyuan Zhang, Shihao Tang, Han Zhang, Tao Pang","doi":"10.1108/ijwis-10-2023-0184","DOIUrl":"https://doi.org/10.1108/ijwis-10-2023-0184","url":null,"abstract":"Purpose\u0000Because of the various advantages of reinforcement learning (RL) mentioned above, this study uses RL to train unmanned aerial vehicles to perform two tasks: target search and cooperative obstacle avoidance.\u0000\u0000Design/methodology/approach\u0000This study draws inspiration from the recurrent state-space model and recurrent models (RPM) to propose a simpler yet highly effective model called the unmanned aerial vehicles prediction model (UAVPM). The main objective is to assist in training the UAV representation model with a recurrent neural network, using the soft actor-critic algorithm.\u0000\u0000Findings\u0000This study proposes a generalized actor-critic framework consisting of three modules: representation, policy and value. This architecture serves as the foundation for training UAVPM. This study proposes the UAVPM, which is designed to aid in training the recurrent representation using the transition model, reward recovery model and observation recovery model. Unlike traditional approaches reliant solely on reward signals, RPM incorporates temporal information. In addition, it allows the inclusion of extra knowledge or information from virtual training environments. This study designs UAV target search and UAV cooperative obstacle avoidance tasks. The algorithm outperforms baselines in these two environments.\u0000\u0000Originality/value\u0000It is important to note that UAVPM does not play a role in the inference phase. This means that the representation model and policy remain independent of UAVPM. Consequently, this study can introduce additional “cheating” information from virtual training environments to guide the UAV representation without concerns about its real-world existence. By leveraging historical information more effectively, this study enhances UAVs’ decision-making abilities, thus improving the performance of both tasks at hand.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GraphQL response data volume prediction based on Code2Vec and AutoML","authors":"Feng Zhang, Youliang Wei, Tao Feng","doi":"10.1108/ijwis-12-2023-0246","DOIUrl":"https://doi.org/10.1108/ijwis-12-2023-0246","url":null,"abstract":"\u0000Purpose\u0000GraphQL is a new Open API specification that allows clients to send queries and obtain data flexibly according to their needs. However, a high-complexity GraphQL query may lead to an excessive data volume of the query result, which causes problems such as resource overload of the API server. Therefore, this paper aims to address this issue by predicting the response data volume of a GraphQL query statement.\u0000\u0000\u0000Design/methodology/approach\u0000This paper proposes a GraphQL response data volume prediction approach based on Code2Vec and AutoML. First, a GraphQL query statement is transformed into a path collection of an abstract syntax tree based on the idea of Code2Vec, and then the query is aggregated into a vector with the fixed length. Finally, the response result data volume is predicted by a fully connected neural network. To further improve the prediction accuracy, the prediction results of embedded features are combined with the field features and summary features of the query statement to predict the final response data volume by the AutoML model.\u0000\u0000\u0000Findings\u0000Experiments on two public GraphQL API data sets, GitHub and Yelp, show that the accuracy of the proposed approach is 15.85% and 50.31% higher than existing GraphQL response volume prediction approaches based on machine learning techniques, respectively.\u0000\u0000\u0000Originality/value\u0000This paper proposes an approach that combines Code2Vec and AutoML for GraphQL query response data volume prediction with higher accuracy.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140077180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TLN-LSTM: an automatic modulation recognition classifier based on a two-layer nested structure of LSTM network for extremely long signal sequences","authors":"Feng Qian, Yongsheng Tu, Chenyu Hou, Bin Cao","doi":"10.1108/ijwis-12-2023-0248","DOIUrl":"https://doi.org/10.1108/ijwis-12-2023-0248","url":null,"abstract":"\u0000Purpose\u0000Automatic modulation recognition (AMR) is a challenging problem in intelligent communication systems and has wide application prospects. At present, although many AMR methods based on deep learning have been proposed, the methods proposed by these works cannot be directly applied to the actual wireless communication scenario, because there are usually two kinds of dilemmas when recognizing the real modulated signal, namely, long sequence and noise. This paper aims to effectively process in-phase quadrature (IQ) sequences of very long signals interfered by noise.\u0000\u0000\u0000Design/methodology/approach\u0000This paper proposes a general model for a modulation classifier based on a two-layer nested structure of long short-term memory (LSTM) networks, called a two-layer nested structure (TLN)-LSTM, which exploits the time sensitivity of LSTM and the ability of the nested network structure to extract more features, and can achieve effective processing of ultra-long signal IQ sequences collected from real wireless communication scenarios that are interfered by noise.\u0000\u0000\u0000Findings\u0000Experimental results show that our proposed model has higher recognition accuracy for five types of modulation signals, including amplitude modulation, frequency modulation, gaussian minimum shift keying, quadrature phase shift keying and differential quadrature phase shift keying, collected from real wireless communication scenarios. The overall classification accuracy of the proposed model for these signals can reach 73.11%, compared with 40.84% for the baseline model. Moreover, this model can also achieve high classification performance for analog signals with the same modulation method in the public data set HKDD_AMC36.\u0000\u0000\u0000Originality/value\u0000At present, although many AMR methods based on deep learning have been proposed, these works are based on the model’s classification results of various modulated signals in the AMR public data set to evaluate the signal recognition performance of the proposed method rather than collecting real modulated signals for identification in actual wireless communication scenarios. The methods proposed in these works cannot be directly applied to actual wireless communication scenarios. Therefore, this paper proposes a new AMR method, dedicated to the effective processing of the collected ultra-long signal IQ sequences that are interfered by noise.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140425258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}