Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Parking space detection is an important part of the automatic parking assistance system. How to use existing sensors to accurately and effectively detect parking spaces is the key problem that has not been solved in the automatic parking system. Advances in Artificial Intelligence and sensing technologies have motivated significant research and development in parking space detection in the automotive field. Firstly, based on extensive investigation of a lot of literature and the latest re-search results, this paper divides parking space detection methods into methods based on traditional visual features and those methods based on deep learning and introduces them separately. Secondly, the advantages and disadvantages of each parking space detection method are analyzed, compared, and summarized. And the benchmark datasets and algorithm evaluation standards commonly used in parking space detection methods are introduced. Finally, the vision-based parking space detection method is summarized, and the future development trend is prospected. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.304061 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Due to the outbreak of the COVID-19, online diagnosis and treatment services have developed rapidly, but it is not easy for patients to choose the appropriate healthcare service in the face of massive amounts of information. This article proposes a multi-dimensional context-aware healthcare service recommendation method, which consists of a healthcare service matching model and a healthcare service ranking model. The former first collects objective knowledge related to doctors and diseases to build a knowledge graph, then matches a group of healthcare services for patients according to the patient’s input; The latter selects 5 indicators from the doctor’s academic level, geographical location, public influence, reputation, etc. to build a TOPSIS model based on the entropy weight method to recommend the most appropriate healthcare services for patients. Finally, taking the patient in Shiyan as an example, the whole process of the method is demonstrated, and the feasibility of the method is verified. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.302658 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Mobile edge computing is playing an increasingly important role in the rise of mobile Internet technology. Services deployed on edge servers nearby mobile users would provide computing capabilities with low latency and high scalability. Usually, a single service is challenging to meet a complex user request, which asks for composing services. With the increasing number of services in the cloud and edge computing environment and the user mobility, selecting appropriate services to meet the complex mobile user’s requests becomes a crucial problem. This paper proposes a modified moth-flame optimization algorithm using overall QoS for service selection. Specifically, the overall QoS of services is calculated by combining the subjective and objective QoS with the ordinal relationship and coefficient of variation, and the moth-flame optimization algorithm is improved by adding the differential evolution algorithm. The experimental results show that the proposed approach outperforms some other services selection approaches. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.302888 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: The mobile edge computing (MEC) model is featured by the ability to provision elastic computing resources close to user requests at the edge of the internet. This paradigm moves traditional digital infrastructure close to mobile networks and extensively reduces application latency for mobile computing tasks like online gaming and video streaming. Nevertheless, it remains a difficulty to provide a effective and performance-guaranteed edge service offloading and migration in the MEC environment. Most existing contributions in this area consider task offloading as a offline decision making process by exploiting transient positions of mobile requesters as model inputs. In this work instead, we develop a predictive-trajectory-aware and online MEC task offloading strategy. Simulations based on real-world MEC deployment datasets and a campus mobile trajectory datasets clearly illustrate that our approach outperforms state-of-the-art ones in terms of effective service rate and migration overhead. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.302639 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Prediction of stock price movement is regarded as a challenging task of financial time series prediction. Due to the complexity and massive financial market data, the research of deep learning approaches for predicting the future price is very difficult. This study attempted to develop a novel framework, named 13f-LSTM, where the AutoRegressive Integrated Moving Average (ARIMA), for the first time, as one of the technical features, Fourier transforms for trend analysis and Long-Short Term Memory (LSTM), including its variants, to forecast the future’s closing prices. Thirteen historical and technical features of stock were selected as inputs of the proposed 13f-LSTM model. Three typical stock market indices in the real world and their corresponding closing prices in 30 trading days are chosen to examine the performance and predictive accuracy of it. The experimental results show that the 13f-LSTM model outperforms other proposed models in both profitability performance and predictive accuracy. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.302640 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Fog computing is a potential solution for the Internet of Things in close connection with things and end-users. Fog computing will easily transfer sensitive data without delaying distributed devices. Moreover, fog computing is more in real-time streaming applications, sensor networks, IoT which need high speed and reliable internet connectivity. Due to the heterogeneous and distributed characteristics, finley distributing the task with computation offloading is a challenging task. Developing an efficient QoE-aware application mapping policy is challenging due to the different user interests. The energy consumption would usually increase after such an algorithm and policy are implemented. In this paper, we enhanced the future from the previous QoE paper by proposing a computation offloading algorithm. The proposed algorithm is to prevent overloading on fog devices. Our proposed solution has been evaluated and compared with other existing solutions, the results show that our proposed solution performs better in terms of execution time, energy consumption, and network usage. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.299017 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: With the rapid development of the mobile internet and the rapid popularization of smart terminal devices, types and content of services are changing with each passing day, these bring serious mobile information overload problems for mobile users. How to provide better service recommendations for users is an urgent problem to be solved. A crowdsourcing service recommendation strategy for mobile scenarios and user trajectory awareness is proposed. First, the location coordinates in the historical log are clustered into regions by clustering algorithms, and then the user's trajectory patterns are mined in different mobile scenarios to extract mobile rules. Furthermore, the mobile rules are extracted and the scenario to which each rule belongs is judged. When performing crowdsourcing service recommendation, the location trajectory and mobile scenario information are perceived in real time, they are used to predict the location area where the user will soon arrive, thereby the crowdsourcing service in the area is pushed to the user. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.299020 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: In cloud computing, an advanced persistent threat (APT) is a cyber-attack that gains access to a network and remains undetected for some time. As well APTs have proven difficult to detect and protect, in the existing system they fail to analyze the path of an outbreak when the monitor and assign a weight to the nodes. If a path for an outbreak is detected the VM is migrated to hosts that do not account for the overloaded problem and underutilized hosts. In addition to the size of resources occupied by the VM thus here the traffic was increased. This paper proposes the Threat-Path Reckon technique that detects the multiple paths through re-identification and the addition of automatic weight for its neighbor nodes. Based on that weighted paths, the Secured Object Emigration technique invokes a mapping function to migrate the VMs. Finally, the data in the VM are stored in a best-fit distribution, thus it provides security but achieves the search overheads. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.299021 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: The use of the Cloud computing has been constantly on the rise. However, there are many challenges associated with the Cloud, such as high bandwidth requirements, data security, vendor lock-in and others. The recent rise of decentralized file systems (DFSs) can help mitigate some of these challenges. However, they have some limitations of their own and the current solutions do not provide any mechanism for implementing access control policies. This becomes a hurdle for migrating sensitive data from the Cloud as the associated authorization policies cannot be migrated to the DFSs. In this paper, the authors address the problem of migrating data, and associated authorization policies, from the Cloud to the DFS. They have applied the approach on the content and policies from an actual Cloud provider and it migrates data from AWS S3 to the IPFS and the resource-based authorization policies specified at AWS are added to a custom blockchain solution. The authors have provided implementation details to justify the practicality of the approach. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 0-0 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.296688 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Harendranath; Vegi, Rodda, Sireesha Pages: 1 - 25 Abstract: This paper proposes an effective and optimal sentiment classification method named Penguin Rider optimization algorithm-based Deep Recurrent Neural Network (PeROA-based Deep RNN) to perform sentiment classification using political reviews. However, the proposed PeROA is developed by incorporating the Penguins Search Optimization Algorithm (PeSOA) with the Rider Optimization Algorithm (ROA). The sentiment classification process is progressed using the Deep RNN classifier, which in turn generate the optimal solution based on the fitness measure. Accordingly, the function with the minimal error value is accepted as the best solution. The sentiment-based features enable the classifier to perform better classification result with respect to the sentiment tweets. However, the proposed PeROA-based Deep RNN obtained better performance using the metrics, like accuracy, sensitivity, specificity, recall, F-measure, thread score, NPV, FPR,FNR and FDR with the values of 92.030%, 92.030%, 92.235%, 92.030%, 92.030%, 92.030%, 92.030%, 3.105%, 3.11%, and 3.105%, respectively. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 1-25 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.299019 Issue No:Vol. 19, No. 1 (2022)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Matsutsuka; Taka, Ogawa, Masatoshi, Toriyama, Yohei, Aso, Noriyasu, Iida, Ichiro Pages: 1 - 22 Abstract: In order to enhance the customer experience, it is important not only to provide functions, but also to respond to changes in environments and requirements. It is a difficult task to evaluate and manage which function with different locations and contents is most valuable to the user's experience without using computationally time-consuming optimization calculations. To address this, this paper is focusing on self-adaptive software technology. The authors built a software adaptation mechanism that can be immediately calculated online using a performance characteristic map and threshold judgment with a learning function and sequential updates. The results confirmed the effectiveness of the mechanism in an application that supports personnel exchange events. Keywords: Web Technologies; Computer Science & IT; Web Services Citation: International Journal of Web Services Research (IJWSR), Volume: 19, Issue: 1 (2022) Pages: 1-22 PubDate: 2022-01-01T05:00:00Z DOI: 10.4018/IJWSR.299018 Issue No:Vol. 19, No. 1 (2022)
Subscription journal
[147 journals]
