International Journal of Web Information Systems最新文献

{"title":"ImageNet classification with Raspberry Pis: federated learning algorithms of local classifiers","authors":"Thanh-Nghi Do, Minh-Thu Tran-Nguyen","doi":"10.1108/ijwis-03-2023-0057","DOIUrl":"https://doi.org/10.1108/ijwis-03-2023-0057","url":null,"abstract":"Purpose This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD and FL-lSVM. These algorithms are designed to address the challenge of large-scale ImageNet classification. Design/methodology/approach The authors’ FL-lSGD and FL-lSVM trains in a parallel and incremental manner to build an ensemble local classifier on Raspberry Pis without requiring data exchange. The algorithms load small data blocks of the local training subset stored on the Raspberry Pi sequentially to train the local classifiers. The data block is split into k partitions using the k-means algorithm, and models are trained in parallel on each data partition to enable local data classification. Findings Empirical test results on the ImageNet data set show that the authors’ FL-lSGD and FL-lSVM algorithms with 4 Raspberry Pis (Quad core Cortex-A72, ARM v8, 64-bit SoC @ 1.5GHz, 4GB RAM) are faster than the state-of-the-art LIBLINEAR algorithm run on a PC (Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32GB RAM). Originality/value Efficiently addressing the challenge of large-scale ImageNet classification, the authors’ novel federated learning algorithms of local classifiers have been tailored to work on the Raspberry Pi. These algorithms can handle 1,281,167 images and 1,000 classes effectively.","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":"29 47","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139147663","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":"A review of in-memory computing for machine learning: architectures, options","authors":"Václav Snášel, Tran Khanh Dang, Josef Kueng, Lingping Kong","doi":"10.1108/ijwis-08-2023-0131","DOIUrl":"https://doi.org/10.1108/ijwis-08-2023-0131","url":null,"abstract":"\u0000Purpose\u0000This paper aims to review in-memory computing (IMC) for machine learning (ML) applications from history, architectures and options aspects. In this review, the authors investigate different architectural aspects and collect and provide our comparative evaluations.\u0000\u0000\u0000Design/methodology/approach\u0000Collecting over 40 IMC papers related to hardware design and optimization techniques of recent years, then classify them into three optimization option categories: optimization through graphic processing unit (GPU), optimization through reduced precision and optimization through hardware accelerator. Then, the authors brief those techniques in aspects such as what kind of data set it applied, how it is designed and what is the contribution of this design.\u0000\u0000\u0000Findings\u0000ML algorithms are potent tools accommodated on IMC architecture. Although general-purpose hardware (central processing units and GPUs) can supply explicit solutions, their energy efficiencies have limitations because of their excessive flexibility support. On the other hand, hardware accelerators (field programmable gate arrays and application-specific integrated circuits) win on the energy efficiency aspect, but individual accelerator often adapts exclusively to ax single ML approach (family). From a long hardware evolution perspective, hardware/software collaboration heterogeneity design from hybrid platforms is an option for the researcher.\u0000\u0000\u0000Originality/value\u0000IMC’s optimization enables high-speed processing, increases performance and analyzes massive volumes of data in real-time. This work reviews IMC and its evolution. Then, the authors categorize three optimization paths for the IMC architecture to improve performance metrics.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":"34 25","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138946936","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":"Efficient knowledge distillation for remote sensing image classification: a CNN-based approach","authors":"Huaxiang Song, Chai Wei, Zhou Yong","doi":"10.1108/ijwis-10-2023-0192","DOIUrl":"https://doi.org/10.1108/ijwis-10-2023-0192","url":null,"abstract":"\u0000Purpose\u0000The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.\u0000\u0000\u0000Design/methodology/approach\u0000This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.\u0000\u0000\u0000Findings\u0000This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.\u0000\u0000\u0000Originality/value\u0000This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":"2 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138972937","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":"FedACQ: adaptive clustering quantization of model parameters in federated learning","authors":"Tingting Tian, Hongjian Shi, Ruhui Ma, Yuan Liu","doi":"10.1108/ijwis-08-2023-0128","DOIUrl":"https://doi.org/10.1108/ijwis-08-2023-0128","url":null,"abstract":"Purpose For privacy protection, federated learning based on data separation allows machine learning models to be trained on remote devices or in isolated data devices. However, due to the limited resources such as bandwidth and power of local devices, communication in federated learning can be much slower than in local computing. This study aims to improve communication efficiency by reducing the number of communication rounds and the size of information transmitted in each round. Design/methodology/approach This paper allows each user node to perform multiple local trainings, then upload the local model parameters to a central server. The central server updates the global model parameters by weighted averaging the parameter information. Based on this aggregation, user nodes first cluster the parameter information to be uploaded and then replace each value with the mean value of its cluster. Considering the asymmetry of the federated learning framework, adaptively select the optimal number of clusters required to compress the model information. Findings While maintaining the loss convergence rate similar to that of federated averaging, the test accuracy did not decrease significantly. Originality/value By compressing uplink traffic, the work can improve communication efficiency on dynamic networks with limited resources.","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":"8 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139222102","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":"A systematic literature review of authorization and access control requirements and current state of the art for different database models","authors":"Aya Khaled Youssef Sayed Mohamed, Dagmar Auer, Daniel Hofer, Josef Küng","doi":"10.1108/ijwis-04-2023-0072","DOIUrl":"https://doi.org/10.1108/ijwis-04-2023-0072","url":null,"abstract":"Purpose Data protection requirements heavily increased due to the rising awareness of data security, legal requirements and technological developments. Today, NoSQL databases are increasingly used in security-critical domains. Current survey works on databases and data security only consider authorization and access control in a very general way and do not regard most of today’s sophisticated requirements. Accordingly, the purpose of this paper is to discuss authorization and access control for relational and NoSQL database models in detail with respect to requirements and current state of the art. Design/methodology/approach This paper follows a systematic literature review approach to study authorization and access control for different database models. Starting with a research on survey works on authorization and access control in databases, the study continues with the identification and definition of advanced authorization and access control requirements, which are generally applicable to any database model. This paper then discusses and compares current database models based on these requirements. Findings As no survey works consider requirements for authorization and access control in different database models so far, the authors define their requirements. Furthermore, the authors discuss the current state of the art for the relational, key-value, column-oriented, document-based and graph database models in comparison to the defined requirements. Originality/value This paper focuses on authorization and access control for various database models, not concrete products. This paper identifies today’s sophisticated – yet general – requirements from the literature and compares them with research results and access control features of current products for the relational and NoSQL database models.","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135043677","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":"A real-time discovery method for vehicle companion via service collaboration","authors":"Zhongmei Zhang, Qingyang Hu, Guanxin Hou, Shuai Zhang","doi":"10.1108/ijwis-07-2023-0112","DOIUrl":"https://doi.org/10.1108/ijwis-07-2023-0112","url":null,"abstract":"Purpose Vehicle companion is one of the most common companion patterns in daily life, which has great value to accident investigation, group tracking, carpooling recommendation and road planning. Due to the complexity and large scale of vehicle sensor streaming data, existing work were difficult to ensure the efficiency and effectiveness of real-time vehicle companion discovery (VCD). This paper aims to provide a high-quality and low-cost method to discover vehicle companions in real time. Design/methodology/approach This paper provides a real-time VCD method based on pro-active data service collaboration. This study makes use of dynamic service collaboration to selectively process data produced by relative sensors, and relax the temporal and spatial constraints of vehicle companion pattern for discovering more potential companion vehicles. Findings Experiments based on real and simulated data show that the method can discover 67% more companion vehicles, with 62% less response time comparing with centralized method. Originality/value To reduce the amount of processing streaming data, this study provides a Service Collaboration-based Vehicle Companion Discovery method based on proactive data service model. And this study provides a new definition of vehicle companion through relaxing the temporal and spatial constraints for discover companion vehicles as many as possible.","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135937978","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":"LoGE: an unsupervised local-global document extension generation in information retrieval for long documents","authors":"Oussama Ayoub, Christophe Rodrigues, Nicolas Travers","doi":"10.1108/ijwis-07-2023-0109","DOIUrl":"https://doi.org/10.1108/ijwis-07-2023-0109","url":null,"abstract":"\u0000Purpose\u0000This paper aims to manage the word gap in information retrieval (IR) especially for long documents belonging to specific domains. In fact, with the continuous growth of text data that modern IR systems have to manage, existing solutions are needed to efficiently find the best set of documents for a given request. The words used to describe a query can differ from those used in related documents. Despite meaning closeness, nonoverlapping words are challenging for IR systems. This word gap becomes significant for long documents from specific domains.\u0000\u0000\u0000Design/methodology/approach\u0000To generate new words for a document, a deep learning (DL) masked language model is used to infer related words. Used DL models are pretrained on massive text data and carry common or specific domain knowledge to propose a better document representation.\u0000\u0000\u0000Findings\u0000The authors evaluate the approach of this study on specific IR domains with long documents to show the genericity of the proposed model and achieve encouraging results.\u0000\u0000\u0000Originality/value\u0000In this paper, to the best of the authors’ knowledge, an original unsupervised and modular IR system based on recent DL methods is introduced.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42977715","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":"Online educational video engagement prediction based on dynamic graph neural networks","authors":"Xiancheng Ou, Yuting Chen, Siwei Zhou, Jiandong Shi","doi":"10.1108/ijwis-05-2023-0083","DOIUrl":"https://doi.org/10.1108/ijwis-05-2023-0083","url":null,"abstract":"\u0000Purpose\u0000With the continuous growth of online education, the quality issue of online educational videos has become increasingly prominent, causing students in online learning to face the dilemma of knowledge confusion. The existing mechanisms for controlling the quality of online educational videos suffer from subjectivity and low timeliness. Monitoring the quality of online educational videos involves analyzing metadata features and log data, which is an important aspect. With the development of artificial intelligence technology, deep learning techniques with strong predictive capabilities can provide new methods for predicting the quality of online educational videos, effectively overcoming the shortcomings of existing methods. The purpose of this study is to find a deep neural network that can model the dynamic and static features of the video itself, as well as the relationships between videos, to achieve dynamic monitoring of the quality of online educational videos.\u0000\u0000\u0000Design/methodology/approach\u0000The quality of a video cannot be directly measured. According to previous research, the authors use engagement to represent the level of video quality. Engagement is the normalized participation time, which represents the degree to which learners tend to participate in the video. Based on existing public data sets, this study designs an online educational video engagement prediction model based on dynamic graph neural networks (DGNNs). The model is trained based on the video’s static features and dynamic features generated after its release by constructing dynamic graph data. The model includes a spatiotemporal feature extraction layer composed of DGNNs, which can effectively extract the time and space features contained in the video's dynamic graph data. The trained model is used to predict the engagement level of learners with the video on day T after its release, thereby achieving dynamic monitoring of video quality.\u0000\u0000\u0000Findings\u0000Models with spatiotemporal feature extraction layers consisting of four types of DGNNs can accurately predict the engagement level of online educational videos. Of these, the model using the temporal graph convolutional neural network has the smallest prediction error. In dynamic graph construction, using cosine similarity and Euclidean distance functions with reasonable threshold settings can construct a structurally appropriate dynamic graph. In the training of this model, the amount of historical time series data used will affect the model’s predictive performance. The more historical time series data used, the smaller the prediction error of the trained model.\u0000\u0000\u0000Research limitations/implications\u0000A limitation of this study is that not all video data in the data set was used to construct the dynamic graph due to memory constraints. In addition, the DGNNs used in the spatiotemporal feature extraction layer are relatively conventional.\u0000\u0000\u0000Originality/value\u0000In this study, the authors propose an online educational video enga","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46178873","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":"Beneath the surface: a bibliometric analysis of the hidden risks and costs of blockchain technology","authors":"Zahid Mahmood, Muhammad Asif, Mohammed Aljuaid, Rab Nawaz Lodhi","doi":"10.1108/ijwis-08-2023-0124","DOIUrl":"https://doi.org/10.1108/ijwis-08-2023-0124","url":null,"abstract":"Purpose\u0000The purpose of this paper is to identify the negative aspects of blockchain technology and to shed the light on most productive years, countries, authors, sources and frequent keywords.\u0000\u0000\u0000Design/methodology/approach\u0000A Web of Science bibliographic data set containing 209 journal articles was evaluated using descriptive and network analytics. A two-step process is adopted in this study; descriptive analysis is initially carried out using RStudio to determine the most productive years, nations, sources and authors, and using co-occurrence of keyword analysis in VOSviewer, the most influential keywords are determined.\u0000\u0000\u0000Findings\u0000The findings reveal that 2022 is the most prolific year in terms of number of publications. It is discovered that China tops the list for having published the most articles. Similarly, the most productive authors are Kumar A and Abhishek K.\u0000\u0000\u0000Originality/value\u0000To the best of the authors’ knowledge, this bibliometric analysis is unique in that it takes a thorough approach to examine the negative aspects of blockchain technology and identify research trends and offer insights that might guide future research and practical solutions.","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136298690","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":"Handling qualitative conditional preference queries in SPARQL: possibilistic logic approach","authors":"Fayçal Touazi, Amel Boustil","doi":"10.1108/ijwis-05-2023-0077","DOIUrl":"https://doi.org/10.1108/ijwis-05-2023-0077","url":null,"abstract":"\u0000Purpose\u0000The purpose of this paper is to address the need for new approaches in locating items that closely match user preference criteria due to the rise in data volume of knowledge bases resulting from Open Data initiatives. Specifically, the paper focuses on evaluating SPARQL qualitative preference queries over user preferences in SPARQL.\u0000\u0000\u0000Design/methodology/approach\u0000The paper outlines a novel approach for handling SPARQL preference queries by representing preferences through symbolic weights using the possibilistic logic (PL) framework. This approach allows for the management of symbolic weights without relying on numerical values, using a partial ordering system instead. The paper compares this approach with numerous other approaches, including those based on skylines, fuzzy sets and conditional preference networks.\u0000\u0000\u0000Findings\u0000The paper highlights the advantages of the proposed approach, which enables the representation of preference criteria through symbolic weights and qualitative considerations. This approach offers a more intuitive way to convey preferences and manage rankings.\u0000\u0000\u0000Originality/value\u0000The paper demonstrates the usefulness and originality of the proposed SPARQL language in the PL framework. The approach extends SPARQL by incorporating symbolic weights and qualitative preferences.\u0000","PeriodicalId":44153,"journal":{"name":"International Journal of Web Information Systems","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45459466","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}