Computer Science and Information Systems最新文献

{"title":"Supporting 5G service orchestration with formal verification","authors":"Peter Backeman, Ashalatha Kunnappilly, C. Seceleanu","doi":"10.2298/csis211001059b","DOIUrl":"https://doi.org/10.2298/csis211001059b","url":null,"abstract":"The 5G communication technology has the ability to create logical net works, called network slices, which are specifically carved to serve particular application domains. Due to the mix of different application criticality, it becomes crucial to verify if the applications? service level agreements are met. In this pa per, we propose a novel framework for modeling and verifying 5G orchestration, considering simultaneous access and admission of new requests to slices as well as virtual network function scheduling and routing. By combining modeling in user friendly UML, with UPPAAL model checking and satisfiability-modulo-theories based model finding, our framework supports both modeling and formal verification of service orchestration. We demonstrate our approach on a e-health case study showing how a user, with no knowledge of formal methods, can model a system in UML and verify that the application meets its requirements.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"18 1","pages":"329-357"},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82185798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inverse halftoning based on sparse representation with boosted dictionary","authors":"Jun Yang, Zihao Liu, Li Chen, Ying Wu, Gang Ke","doi":"10.2298/csis220808022y","DOIUrl":"https://doi.org/10.2298/csis220808022y","url":null,"abstract":"Halftone image is widely used in printing and scanning equipment. It is significant for the halftone image to be preserved and processed. For the different resolution of the display devices, the processing and displaying of halftone image are faced with great challenges, such as Moore pattern and image blur ring. The inverse halftone technique is required to remove the halftone screen. In this paper, we propose an inverse halftone algorithm based on sparse representation with the dictionary learned by two steps: deconvolution and sparse optimization in the transform domain to remove the noise. The main contributions of this paper include three aspects: first, we analysis the denoising effects for different training sets and the dictionary; Then we propose the denoising algorithm through adaptively learning the dictionary, which iteratively remove the noise of the training set and improve the dictionary; Then the inverse halftone algorithm is proposed. Finally, we verify that the noise level in the error diffusion linear model is fixed, and the noise level is only related to the diffusion operator. Experimental results show that the proposed algorithm has better PSNR and visual performance than state-of-the-art methods. The codes and constructed models are available at https://github.com/juneryoung2022/IH-WNNM.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"2 1","pages":"813-829"},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82275490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secure cloud internet of vehicles based on blockchain and data transmission scheme of map/reduce","authors":"Hua-Yi Lin","doi":"10.2298/csis220921056l","DOIUrl":"https://doi.org/10.2298/csis220921056l","url":null,"abstract":"Over the past few years, because of the popularity of the Internet of vehicles and cloud computing, the exchange of group information between vehicles is no longer out of reach. Through WiFi/5G wireless communication protocol, vehicles can instantly deliver traffic conditions and accidents to the back end or group vehicles traveling together, which can reduce traffic congestion and accidents. In addition, vehicles transmit real-time road conditions to the cloud vehicle management center, which can also share real-time road conditions and improve the road efficiency for pedestrians and drivers. However, the transmission of information in an open environment raises the issue of personal information security. Most of the security mechanisms provided by the existing Internet of vehicles require centralized authentication servers, which increase the burden of certificate management and computing. Moreover, the road side unit as a decentralized authentication center may be open to hacking or modification, but due to personal privacy and security concerns, vehicle-to-vehicle is not willing to share information with each other. Therefore, this study is conducted through blockchain to ensure the security of vehicle-based information transmission. Moreover, the elliptic curve Diffie-Hellman (ECDH) key exchange protocol and a secure conference key mechanism with direct user confirmation combined with the back-end cloud platform Map/Reduce is proposed to ensure the identities of Mappers and Reducers that participate in the cloud operation, avoid malicious participants to modify the transmission information, so as to achieve secure Map/Reduce operations, and improves vehicle and passenger traffic safety.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"1 1","pages":"137-156"},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87857815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of smart city construction and optimization of city brand model under neural networks","authors":"Yingji Li, Yufeng Qian, Qiang Li, Linna Li","doi":"10.2298/csis220715010l","DOIUrl":"https://doi.org/10.2298/csis220715010l","url":null,"abstract":"The study aims to avoid the phenomenon that thousand cities seem the same in the construction of smart cities and the efforts of all walks of life are jointed to implement the construction of smart cities and the creation of city brands. First, the basic theory of smart city construction is introduced. Second, the restricting and promoting factors influencing smart city construction and development are analyzes, and the evaluation system of smart city development is established. Then, the model for smart city construction and development based on the neural network is implemented. Finally, some domestic cities are selected as the dataset to build a training model, and the city brand optimization strategy is proposed. On this basis, an evaluation system for smart city development based on the intelligent neural network and Grey relational analysis Back Propagation Neural Network (GRA-BPNN) is obtained. The entropy weight method (EWM), grey relational analysis (GRA) method and the evaluation method based on Technique for Order Preference by Similarity to an Ideal Solutionv (TOPSIS) are regarded as the members of the control group, and the results of different methods for evaluating the development of smart cities are compared. The results show that the modeling of smart city construction based on neural networks can help to implement an evaluation model for smart city construction and development, and it can help evaluate smart city construction and development accurately. And then the corresponding strategies are proposed to speed up the construction of smart cities with its local characteristics, and then city brands are built. Compared with other evaluation algorithms, the performance of the algorithm proposed is better and more stable and the evaluation results are more reasonable than those of the others, which can prove that the evaluation algorithm is feasible and scientific. This study provides a new idea for the application of deep learning to smart city construction and city brand building","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"16 1","pages":"573-593"},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74958698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Landslide detection based on efficient residual channel attention mechanism network and faster R-CNN","authors":"Yabing Jin, Ou Ou, Shanwen Wang, Yijun Liu, Haoqing Niu, X. Leng","doi":"10.2298/csis220831003j","DOIUrl":"https://doi.org/10.2298/csis220831003j","url":null,"abstract":"Accurate landslide detection plays an important role in land planning, disaster prediction and disaster relief. At present, field investigation and exploration based on professional personnel is the most widely used landslide mapping and detection technology, but this method consumes a lot of manpower and material resources and is inefficient. With the development of artificial intelligence, landslide identification and target detection based on deep learning have attracted more and more attention due to their remarkable advantages over traditional technologies. It is a technical problem to identify landslides from satellite remote sensing images. Although there are some methods at present, there is still room for improvement in the target detection algorithm of landslides against the background of the diversity and complexity of landslides. In this paper, target detection algorithm models such as Faster R-CNN apply to landslide recognition and detection tasks, and various commonly used recognition and detection algorithm network structures are used as the basic models for landslide recognition. Efficient residual channel soft thresholding attention mechanism algorithm (ERCA) is proposed, which intends to reduce the background noise of images in complex environments by means of deep learning adaptive soft thresholding to improve the feature learning capability of deep learning target detection algorithms. ERCA is added to the backbone network of the target detection algorithm for basic feature extraction to enhance the feature extraction and expression capability of the network. During the experiment ERCA combined with ResNet50, ResNet101 and other backbone networks, the objective indicators of detection results such as AP50 (Average Precision at IOU=0.50), AP75 (Average Precision at IOU=0.75) and AP (Average Precision) were improved, and the AP values were all improved to about 4%, and the final detection results using ResNet101 combined with ERCA as the backbone network reached 76.4% AP value. ERCA and other advanced channel attention networks such as ECA (Efficient Channel Attention for Deep Convolutional Neural Networks) and SENet (Squeeze-and-Excitation Networks) are fused into the backbone network of the target detection algorithm and experimented on the landslide identification detection task, and the detection results are that the objective detection indexes AP50, AP75, AP, etc. are higher for ERCA compared with other channel attention, and the subjective detection image detection effect and feature map visualization display are also better. We released our code at: https://github.com/fluoritess/Efficient-residual-channel-attention-mechanism-network-and-Faster-R-CNN.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"1 1","pages":"893-910"},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81281257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Probabilistic reasoning for diagnosis prediction of Coronavirus disease based on probabilistic ontology","authors":"Messaouda Fareh, Ishak Riali, Hafsa Kherbache, Marwa Guemmouz","doi":"10.2298/csis220829035f","DOIUrl":"https://doi.org/10.2298/csis220829035f","url":null,"abstract":"The novel Coronavirus has been declared a pandemic by the World Health Organization (WHO). Predicting the diagnosis of COVID-19 is essential for disease cure and control. The paper?s main aim is to predict the COVID-19 diagnosis using probabilistic ontologies to address the randomness and incomplete ness of knowledge. Our approach begins with constructing the entities, attributes, and relationships of COVID-19 ontology, by extracting symptoms and risk factors. The probabilistic components of COVID-19 ontology are developed by creating a Multi-Entity Bayesian Network, then determining its components, with the different nodes, as probability distribution linked to various nodes. We use probabilistic in ference for predicting COVID-19 diagnosis, using the Situation-Specific Bayesian Network (SSBN). To validate the solution, an experimental study is conducted on real cases, comparing the results of existing machine learning methods, our solution presents an encouraging result and, therefore enables fast medical assistance.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"54 84 1","pages":"1109-1132"},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91076399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A study of identity authentication using blockchain technology in a 5G multi-type network environment","authors":"Jui-Hung Kao, Yu-Yu Yen, Wei-Chen Wu, Horng-Twu Liaw, Shiou-Wei Fan, Yi-Chen Kao","doi":"10.2298/csis221115070k","DOIUrl":"https://doi.org/10.2298/csis221115070k","url":null,"abstract":"The 5G technology, known for its large bandwidth, high speed, low latency, and multi-connection capabilities, significantly accelerates digital transformation in enterprises, especially in addressing factory automation challenges. It facilitates efficient machine-to-machine (M2M) and device-to-device (D2D) connectivity, ensuring rapid data transfer and seamless process convergence under 5G standards. Although 5G offers substantial communication and low latency benefits, its limited indoor coverage requires the deployment of decentralized antennas or small base stations. In contrast, Wi-Fi 6 seamlessly complements 5G, providing superior indoor mobile connectivity. This integration is crucial for businesses looking to accelerate digital transformation. To optimize 5G, the deployment of devices such as bypass switches, SDN switches, and MEC in the 5G Local Breakout network enables user access control and fast authentication. Real-world validation confirms the effectiveness of these measures, which are expected to lead to the future of 5G mobile networks.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"365 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135446193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Applying spin checker on 5G EAP-TLS authentication protocol analysis","authors":"Qianli Wang","doi":"10.2298/csis230611068w","DOIUrl":"https://doi.org/10.2298/csis230611068w","url":null,"abstract":"Currently, there is relatively little formal analysis and verification work on the 5G EAP-TLS authentication protocol. In this paper, we use the model checker SPIN to perform a formal analysis of the 5G EAP-TLS authentication protocol. Firstly, we analyze the process of the 5G EAP-TLS authentication protocol and abstract it to obtain a formal model of the protocol. Then, we describe the construction of the protocol model based on the Promela language. The unique feature of this paper is the replacement of the hash value of the 5G EAP-TLS authentication protocol with the message content field encrypted by an unknown subject public key. This is because the Promela language in SPIN has an eval function that can check the value of each field. This can replace the function of the hash function and make the Promela model construction more portable. The paper analyzes the attack paths of the protocol and reveals design flaws that undermine the expected identity authentication attributes and secret consistency of the protocol. The results not only provide a comprehensive understanding of the security properties of the 5G EAP-TLS authentication protocol but also offer valuable insights and guidance for the verification of the protocol's security properties, security design, and optimization of protocol implementation and interoperability.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135446441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D convolutional long short-term encoder-decoder network for moving object segmentation","authors":"Anil Turker, Ender Eksioglu","doi":"10.2298/csis230129044t","DOIUrl":"https://doi.org/10.2298/csis230129044t","url":null,"abstract":"Moving object segmentation (MOS) is one of the important and well studied computer vision tasks that is used in a variety of applications, such as video surveillance systems, human tracking, self-driving cars, and video compression. While traditional approaches to MOS rely on hand-crafted features or background modeling, deep learning methods using Convolution Neural Networks (CNNs) have been shown to be more effective in extracting features and achieving better accuracy. However, most deep learning-based methods for MOS offer scene-dependent solutions, leading to reduced performance when tested on previously unseen video content. Because spatial features are insufficient to represent the motion information, the spatial and temporal features should be used together to succeed in un seen videos. To address this issue, we propose the MOS-Net deep framework, an encoder-decoder network that combines spatial and temporal features using the flux tensor algorithm, 3D CNNs, and ConvLSTM in its different variants. MOS-Net 2.0 is an enhanced version of the base MOS-Net structure, where additional ConvL STM modules are added to 3D CNNs for extracting long-term spatiotemporal features. In the final stage of the framework the output of the encoder-decoder network, the foreground probability map, is thresholded for producing a binary mask where moving objects are in the foreground and the rest forms the background. In addition, an ablation study has been conducted to evaluate different combinations as inputs to the proposed network, using the ChangeDetection2014 (CDnet2014) which in cludes challenging videos such as those with dynamic backgrounds, bad weather, and illumination changes. In most approaches, the training and test strategy are not announced, making it difficult to compare the algorithm results. In addition, the pro posed method can be evaluated differently as video-optimized or video-agnostic. In video-optimized approaches, the training and test set is obtained randomly and sep arated from the overall dataset. The results of the proposed method are compared with competitive methods from the literature using the same evaluation strategy. It has been observed that the introduced MOS networks give highly competitive re sults on the CDnet2014 dataset. The source code for the simulations provided in this work is available online.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136206823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards addressing item cold-start problem in collaborative filtering by embedding agglomerative clustering and FP-growth into the recommendation system","authors":"Eyad Kannout, Michał Grodzki, Marek Grzegorowski","doi":"10.2298/csis221116052k","DOIUrl":"https://doi.org/10.2298/csis221116052k","url":null,"abstract":"This paper introduces a frequent pattern mining framework for recommender systems (FPRS) - a novel approach to address the items? cold-start problem. This difficulty occurs when a new item hits the system, and properly handling such a situation is one of the key success factors of any deployment. The article proposes several strategies to combine collaborative and content-based filtering methods with frequent items mining and agglomerative clustering techniques to mitigate the cold-start problem in recommender systems. The experiments evaluated the developed methods against several quality metrics on three benchmark datasets. The conducted study confirmed usefulness of FPRS in providing apt outcomes even for cold items. The presented solution can be integrated with many different approaches and further extended to make up a complete and standalone RS.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136208670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}