PeerJ Computer Science最新文献

{"title":"Detection of COVID-19 using deep learning on x-ray lung images.","authors":"AbdAlRahman Odeh,&nbsp;Ayah Alomar,&nbsp;Shadi Aljawarneh","doi":"10.7717/peerj-cs.1082","DOIUrl":"https://doi.org/10.7717/peerj-cs.1082","url":null,"abstract":"<p><p>COVID-19 is a widespread deadly virus that directly affects the human lungs. The spread of COVID-19 did not stop at humans but also reached animals, so it was necessary to limit it is spread and diagnose cases quickly by applying a quarantine to the infected people. Recently x-ray lung images are used to determine the infection and from here the idea of this research came to use deep learning techniques to analyze x-ray lung images publicly available on Kaggle to possibly detect COVID-19 infection. In this article, we have proposed a method to possibly detect the COVID-19 by analyzing the X-ray images and applying a number of deep learning pre-trained models such as InceptionV3, DenseNet121, ResNet50, and VGG16, and the results are compared to determine the best performance model and accuracy with the least loss for our dataset. Our evaluation results showed that the best performing model for our dataset is ResNet50 with accuracies of 99.99%, 99.50%, and 99.44% for training, validation, and testing respectively followed by DenseNet121, InceptionV3, and finally VGG16.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1082"},"PeriodicalIF":3.8,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9575860/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"40573318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FDup: a framework for general-purpose and efficient entity deduplication of record collections.","authors":"Michele De Bonis,&nbsp;Paolo Manghi,&nbsp;Claudio Atzori","doi":"10.7717/peerj-cs.1058","DOIUrl":"https://doi.org/10.7717/peerj-cs.1058","url":null,"abstract":"<p><p>Deduplication is a technique aiming at identifying and resolving duplicate metadata records in a collection. This article describes FDup (Flat Collections Deduper), a general-purpose software framework supporting a complete deduplication workflow to manage big data record collections: metadata record data model definition, identification of candidate duplicates, identification of duplicates. FDup brings two main innovations: first, it delivers a full deduplication framework in a single easy-to-use software package based on Apache Spark Hadoop framework, where developers can customize the optimal and parallel workflow steps of blocking, sliding windows, and similarity matching function via an intuitive configuration file; second, it introduces a novel approach to improve performance, beyond the known techniques of \"blocking\" and \"sliding window\", by introducing a smart similarity matching function T-match. T-match is engineered as a decision tree that drives the comparisons of the fields of two records as branches of predicates and allows for successful or unsuccessful early-exit strategies. The efficacy of the approach is proved by experiments performed over big data collections of metadata records in the OpenAIRE Research Graph, a known open access knowledge base in Scholarly communication.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1058"},"PeriodicalIF":3.8,"publicationDate":"2022-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9575841/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"40656161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A learning-based synthesis approach of reward asynchronous probabilistic games against the linear temporal logic winning condition.","authors":"Wei Zhao,&nbsp;Zhiming Liu","doi":"10.7717/peerj-cs.1094","DOIUrl":"https://doi.org/10.7717/peerj-cs.1094","url":null,"abstract":"<p><p>The traditional synthesis problem is usually solved by constructing a system that fulfills given specifications. The system is constantly interacting with the environment and is opposed to the environment. The problem can be further regarded as solving a two-player game (the system and its environment). Meanwhile, stochastic games are often used to model reactive processes. With the development of the intelligent industry, these theories are extensively used in robot patrolling, intelligent logistics, and intelligent transportation. However, it is still challenging to find a practically feasible synthesis algorithm and generate the optimal system according to the existing research. Thus, it is desirable to design an incentive mechanism to motivate the system to fulfill given specifications. This work studies the learning-based approach for strategy synthesis of reward asynchronous probabilistic games against linear temporal logic (LTL) specifications in a probabilistic environment. An asynchronous reward mechanism is proposed to motivate players to gain maximized rewards by their positions and choose actions. Based on this mechanism, the techniques of the learning theory can be applied to transform the synthesis problem into the problem of computing the expected rewards. Then, it is proven that the reinforcement learning algorithm provides the optimal strategies that maximize the expected cumulative reward of the satisfaction of an LTL specification asymptotically. Finally, our techniques are implemented, and their effectiveness is illustrated by two case studies of robot patrolling and autonomous driving.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1094"},"PeriodicalIF":3.8,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455281/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33460849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic review on modification to the <i>ad-hoc</i> on-demand distance vector routing discovery mechanics.","authors":"Ibrahim Alameri,&nbsp;Jitka Komarkova,&nbsp;Tawfik Al-Hadhrami,&nbsp;Ahmad Lotfi","doi":"10.7717/peerj-cs.1079","DOIUrl":"https://doi.org/10.7717/peerj-cs.1079","url":null,"abstract":"<p><p>Mobile <i>ad-hoc</i> networks (MANETs) and wireless mesh networks (WMNs) are used in a variety of research areas, including the military, industry, healthcare, agriculture, the Internet of Things (IoT), transportation, and smart cities. The swift advancement in MANET technology is the driving force behind this rising adoption rate. Routing over MANET is a critical problem due to the dynamic nature of the link qualities, even when nodes are static. A key challenge in MANETs is the need for an efficient routing protocol that establishes a route according to certain performance metrics related to the link quality. The routing protocols utilised by the nodes in WMNs and MANETs are distinct. Nodes in both types of networks exchange data packets through the routing protocols. For this highly mobile network, the <i>ad-hoc</i> On-Demand Distance Vector (AODV) routing protocol has been suggested as a possible solution. Recent years have attracted researchers' attention to AODV since it is a routing technique for <i>ad-hoc</i> networks that prevents looping. The architecture of this routing protocol considers several factors, including the mobility of nodes, the failure of connection links, and the loss of packets. In this systematic review, one of the key focuses is bringing attention to the classic AODV, which was developed after discussing the recent development of several versions of AODV. The AODV routing protocol performs a path strength check to generate a more reliable and secure route between the source and destination nodes. In AODV, investigations demonstrate advances in both the format protocol approach and the network simulation-2 (NS-2), and these improvements were made in the same scenario used to revitalise AODV. It has been discovered that the AODV is more effective in several aspects, such as throughput, end-to-end delay, packet delivery ratio (PDR), energy consumption, jitter, packet loss ratio, and network overhead. Furthermore, this paper presents this systematic review based on AODV modifications in the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). It also provides a methodological framework for the papers' selection.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1079"},"PeriodicalIF":3.8,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455269/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33466629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Constructing marine expert management knowledge graph based on Trellisnet-CRF.","authors":"Jiajing Wu,&nbsp;Zhiqiang Wei,&nbsp;Dongning Jia,&nbsp;Xin Dou,&nbsp;Huo Tang,&nbsp;Nannan Li","doi":"10.7717/peerj-cs.1083","DOIUrl":"https://doi.org/10.7717/peerj-cs.1083","url":null,"abstract":"<p><p>Creating and maintaining a domain-specific database of research institutions, academic experts and scholarly literature is essential to expanding national marine science and technology. Knowledge graphs (KGs) have now been widely used in both industry and academia to address real-world problems. Despite the abundance of generic KGs, there is a vital need to build domain-specific knowledge graphs in the marine sciences domain. In addition, there is still not an effective method for named entity recognition when constructing a knowledge graph, especially when including data from both scientific and social media sources. This article presents a novel marine science domain-based knowledge graph framework. This framework involves capturing marine domain data into KG representations. The proposed approach utilizes various entity information based on marine domain experts to enrich the semantic content of the knowledge graph. To enhance named entity recognition accuracy, we propose a novel TrellisNet-CRF model. Our experiment results demonstrate that the TrellisNet-CRF model reached a 96.99% accuracy rate for marine domain named entity recognition, which outperforms the current state-of-the-art baseline. The effectiveness of the TrellisNet-CRF module was then further demonstrated and confirmed on entity recognition and visualization tasks.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1083"},"PeriodicalIF":3.8,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455288/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33460791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An introduction of preference based stepping ahead firefly algorithm for the uncapacitated examination timetabling.","authors":"Ravneil Nand,&nbsp;Bibhya Sharma,&nbsp;Kaylash Chaudhary","doi":"10.7717/peerj-cs.1068","DOIUrl":"https://doi.org/10.7717/peerj-cs.1068","url":null,"abstract":"<p><p>In recent times, there has been a growing attention to intelligent optimization algorithms centred on swarm principles such as the firefly algorithm (FA). It was proposed for the continuous domain that mimics the attraction of fireflies to flashing light and has been used in discrete domains <i>via</i> modification. A discrete domain that is a major challenge in most higher education institutes (HEI) is examination timetabling. This article presents a new methodology based on FA for uncapacitated examination timetabling problems (UETP) where the proposed method is an extension of earlier work by the authors on the continuous domain. UETP is considered in this article as it is a university examination timetabling problem, which is still an active research area and has not been solved by FA algorithm as per authors knowledge. The proposed method concentrates on solving the initial solution using discrete FA where it consolidates the reordering of examinations and slots through a heuristic ordering known as neighborhood search. Three neighborhoods are employed in this research, where one is used during the initialization phase while two are utilized during solution improvement phase. Later, through preference parameters, a novel stepping ahead mechanism is used, which employs neighborhood searches built on previous searches. The proposed method is tested with 12 UETP problems where the preference based stepping ahead FA creates comparative results to the best ones available in the literature for the Toronto exam timetabling dataset. The results obtained are proof of concept at the preliminary stage and require further experiments on other educational datasets such as the second international timetable competition benchmark sets. The newly introduced preference based stepping ahead mechanism takes advantage of the current best solution space where it exploits the solution space for better solutions. This paves the way for researchers to utilize the mechanism in other domains such as robotics, <i>etc</i>.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1068"},"PeriodicalIF":3.8,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455270/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33460851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-intent based multi-policy relay contrastive learning for sequential recommendation.","authors":"Weiqiang Di","doi":"10.7717/peerj-cs.1088","DOIUrl":"https://doi.org/10.7717/peerj-cs.1088","url":null,"abstract":"<p><p>Sequential recommendations have become a trending study for their ability to capture dynamic user preference. However, when dealing with sparse data, they still fall short of expectations. The recent contrastive learning (CL) has shown potential in mitigating the issue of data sparsity. Many item representations are destined to be poorly learned due to data sparsity. It is better to pay more attention to learn a set of influential latent intents that have greater impacts on the sequence evolution. In this article, we devise a novel multi-intent self-attention module, which modifies the self-attention mechanism to break down the user behavior sequences to multiple latent intents that identify the different tastes and inclinations of users. In addition to the above change in the model architecture, we also extend in dealing with multiple contrastive tasks. Specifically, some data augmentations in CL can be very different. Together they cannot cooperate well, and may stumbling over each other. To solve this problem, we propose a multi-policy relay training strategy, which divides the training into multiple stages based on the number of data augmentations. In each stage we optimize the relay to the best on the basis of the previous stage. This can combine the advantage of different schemes and make the best use of them. Experiments on four public recommendation datasets demonstrate the superiority of our model.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1088"},"PeriodicalIF":3.8,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455276/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33460853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sentiment analysis techniques, challenges, and opportunities: Urdu language-based analytical study.","authors":"Muhammad Irzam Liaqat,&nbsp;Muhammad Awais Hassan,&nbsp;Muhammad Shoaib,&nbsp;Syed Khaldoon Khurshid,&nbsp;Mohamed A Shamseldin","doi":"10.7717/peerj-cs.1032","DOIUrl":"https://doi.org/10.7717/peerj-cs.1032","url":null,"abstract":"<p><p>Sentiment analysis in research involves the processing and analysis of sentiments from textual data. The sentiment analysis for high resource languages such as English and French has been carried out effectively in the past. However, its applications are comparatively few for resource-poor languages due to a lack of textual resources. This systematic literature explores different aspects of Urdu-based sentiment analysis, a classic case of poor resource language. While Urdu is a South Asian language understood by one hundred and sixty-nine million people across the planet. There are various shortcomings in the literature, including limitation of large corpora, language parsers, and lack of pre-trained machine learning models that result in poor performance. This article has analyzed and evaluated studies addressing machine learning-based Urdu sentiment analysis. After searching and filtering, forty articles have been inspected. Research objectives have been proposed that lead to research questions. Our searches were organized in digital repositories after selecting and screening relevant studies. Data was extracted from these studies. Our work on the existing literature reflects that sentiment classification performance can be improved by overcoming the challenges such as word sense disambiguation and massive datasets. Furthermore, Urdu-based language constructs, including language parsers and emoticons, context-level sentiment analysis techniques, pre-processing methods, and lexical resources, can also be improved.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1032"},"PeriodicalIF":3.8,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9454799/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33460403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An enhanced CNN-LSTM remaining useful life prediction model for aircraft engine with attention mechanism.","authors":"Hao Li,&nbsp;Zhuojian Wang,&nbsp;Zhe Li","doi":"10.7717/peerj-cs.1084","DOIUrl":"https://doi.org/10.7717/peerj-cs.1084","url":null,"abstract":"<p><p>Remaining useful life (RUL) prediction is one of the key technologies of aircraft prognosis and health management (PHM) which could provide better maintenance decisions. In order to improve the accuracy of aircraft engine RUL prediction under real flight conditions and better meet the needs of PHM system, we put forward an improved CNN-LSTM model based on the convolutional block attention module (CBAM). First, the features of aircraft engine operation data are extracted by multi-layer CNN network, and then the attention mechanism is processed by CBAM in channel and spatial dimensions to find key variables related to RUL. Finally, the hidden relationship between features and service time is learned by LSTM and the predicted RUL is output. Experiments were conducted using C-MPASS dataset. Experimental results indicate that our prediction model has feasibility. Compared with other state-of-the-art methods, the RMSE of our method decreased by 17.4%, and the score of the prediction model was improved by 25.9%.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1084"},"PeriodicalIF":3.8,"publicationDate":"2022-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455287/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33460788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clone detection for business process models.","authors":"Mahdi Saeedi Nikoo,&nbsp;Önder Babur,&nbsp;Mark van den Brand","doi":"10.7717/peerj-cs.1046","DOIUrl":"https://doi.org/10.7717/peerj-cs.1046","url":null,"abstract":"<p><p>Models are key in software engineering, especially with the rise of model-driven software engineering. One such use of modeling is in business process modeling, where models are used to represent processes in enterprises. As the number of these process models grow in repositories, it leads to an increasing management and maintenance cost. Clone detection is a means that may provide various benefits such as repository management, data prepossessing, filtering, refactoring, and process family detection. In model clone detection, highly similar model fragments are mined from larger model repositories. In this study, we have extended SAMOS (Statistical Analysis of Models) framework for clone detection of business process models. The framework has been developed to support different types of analytics on models, including clone detection. We present the underlying techniques utilized in the framework, as well as our approach in extending the framework. We perform three experimental evaluations to demonstrate the effectiveness of our approach. We first compare our tool against the Apromore toolset for a pairwise model similarity using a synthetic model mutation dataset. As indicated by the results, SAMOS seems to outperform Apromore in the coverage of the metrics in pairwise similarity of models. Later, we do a comparative analysis of the tools on model clone detection using a dataset derived from the SAP Reference Model Collection. In this case, the results show a better precision for Apromore, while a higher recall measure for SAMOS. Finally, we show the additional capabilities of our approach for different model scoping styles through another set of experimental evaluations.</p>","PeriodicalId":503620,"journal":{"name":"PeerJ Computer Science","volume":" ","pages":"e1046"},"PeriodicalIF":3.8,"publicationDate":"2022-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9454782/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33460397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}