Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00013
Weiwei Xie, Mingyan He, Bo Tang
This paper presents a study of examining the statistical correlation between wildfire and weather by mining historical spatial and temporal wildfire and climate data. Large wildfires have been recently becoming more frequent, intense and destructive in the West of United States. The occurrence of wildfires can be determined by many human and natural factors, such as the availability of fuels, physical settings, and weather conditions, among which weather is of great interest and importance for wildfire forecasting. The availability of landscape fire data sets and weather data sets now enables the analysis of correlation between wildfire and weather which indicates the possibility of wildfire for given weather conditions in one region. This paper investigates the relation between wildfire and drought conditions in California and visualize the results using geographic information system (GIS) computing technology. Our data analysis findings show a high correlation between the normalized number of wildfires per forest unit area and drought severity, illustrating the potential of forecasting wildfire using weather data.
{"title":"Data-Enabled Correlation Analysis between Wildfire and Climate using GIS","authors":"Weiwei Xie, Mingyan He, Bo Tang","doi":"10.1109/ICICT50521.2020.00013","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00013","url":null,"abstract":"This paper presents a study of examining the statistical correlation between wildfire and weather by mining historical spatial and temporal wildfire and climate data. Large wildfires have been recently becoming more frequent, intense and destructive in the West of United States. The occurrence of wildfires can be determined by many human and natural factors, such as the availability of fuels, physical settings, and weather conditions, among which weather is of great interest and importance for wildfire forecasting. The availability of landscape fire data sets and weather data sets now enables the analysis of correlation between wildfire and weather which indicates the possibility of wildfire for given weather conditions in one region. This paper investigates the relation between wildfire and drought conditions in California and visualize the results using geographic information system (GIS) computing technology. Our data analysis findings show a high correlation between the normalized number of wildfires per forest unit area and drought severity, illustrating the potential of forecasting wildfire using weather data.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126341351","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00011
Nabil Almashfi, Lunjin Lu
JavaScript is a scripting language that is used for creating web pages. It is widely used and a top contender in realworld usage. JavaScript has many dynamic features that makes it challenging to static analysis. Arrays and objects are one aspect that needs more attention. Array elements are inherently sparse where elements can be added at noncontiguous locations. Object properties can be dynamically accessed and they can also store values of different types. Existing JavaScript static analyzers use constant propagation domains that lose huge amount of precision when analyzing arrays and objects. In this paper, we propose a string abstract domain that is capable of capturing precise information about arrays and objects. The domain we propose provides useful information for the detection of some errors such as the attempt to access a nonexistent element or property. We also define the abstract semantics of some crucial operations over this domain.
{"title":"Precise String Domain for Analyzing JavaScript Arrays and Objects","authors":"Nabil Almashfi, Lunjin Lu","doi":"10.1109/ICICT50521.2020.00011","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00011","url":null,"abstract":"JavaScript is a scripting language that is used for creating web pages. It is widely used and a top contender in realworld usage. JavaScript has many dynamic features that makes it challenging to static analysis. Arrays and objects are one aspect that needs more attention. Array elements are inherently sparse where elements can be added at noncontiguous locations. Object properties can be dynamically accessed and they can also store values of different types. Existing JavaScript static analyzers use constant propagation domains that lose huge amount of precision when analyzing arrays and objects. In this paper, we propose a string abstract domain that is capable of capturing precise information about arrays and objects. The domain we propose provides useful information for the detection of some errors such as the attempt to access a nonexistent element or property. We also define the abstract semantics of some crucial operations over this domain.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"349 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125627816","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00010
A. Rabello, Robison Cris Brito, F. Favarim, A. Weitzenfeld, E. Todt
This paper presents a mobile app developed to optimize the drone flight in a precision agriculture scenario. The Android platform was chosen, once it have free tools for development and there are many different API that could be used to solve this problem. For map presentation, as well as geocoding manipulation, Google tools were used. For the optimization, an algorithm based on recursive auctions was used, which has the characteristic of finding feasible solutions even in complex scenarios. The app has been tested and achieved feasible results for large scenarios with over a thousand waypoints in just few minutes, even running on a mobile device. It highlights the mobile app, and the recursive auction algorithm, it is an important solution for drone flight optimization in rural areas, where there is usually no possibility to run the application on traditional computers, as usually there is no access to the Internet.
{"title":"Mobile System for Optimized Planning to Drone Flight applied to the Precision Agriculture","authors":"A. Rabello, Robison Cris Brito, F. Favarim, A. Weitzenfeld, E. Todt","doi":"10.1109/ICICT50521.2020.00010","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00010","url":null,"abstract":"This paper presents a mobile app developed to optimize the drone flight in a precision agriculture scenario. The Android platform was chosen, once it have free tools for development and there are many different API that could be used to solve this problem. For map presentation, as well as geocoding manipulation, Google tools were used. For the optimization, an algorithm based on recursive auctions was used, which has the characteristic of finding feasible solutions even in complex scenarios. The app has been tested and achieved feasible results for large scenarios with over a thousand waypoints in just few minutes, even running on a mobile device. It highlights the mobile app, and the recursive auction algorithm, it is an important solution for drone flight optimization in rural areas, where there is usually no possibility to run the application on traditional computers, as usually there is no access to the Internet.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"876 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133474044","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00082
M. M. Tulu, Sultan Feisso, Ronghui Hou, Talha Younas
Mobile Social Network (MSN) is attracting the attention of many researchers so as to leverage cellular links by offloading the mobile traffic load via device-to-device communications. Therefore, applying an effective algorithm to identify influential spreaders in MSN is playing a key role. In this paper, a Content Spreading Efficiency (CSE) algorithm, which considers the degree and the number of contact times of a node with its neighbors and the neighbors' friends, is proposed. Also, it considers the nodes' topological position to determine the efficiency of the node to spread content in the network. The performance of CSE strategy is evaluated by Susceptible Infected-Recovered (SIR) model. The results demonstrate the effectiveness of CSE strategy to select important nodes to spread content in MSNs.
移动社交网络(Mobile Social Network, MSN)是一种利用蜂窝链路，通过设备对设备的通信来卸载移动流量负荷的网络，正受到众多研究者的关注。因此，应用一种有效的算法来识别MSN中有影响力的传播者是至关重要的。本文提出了一种内容传播效率(CSE)算法，该算法考虑了节点与其邻居和邻居的朋友的接触程度和次数。同时考虑节点的拓扑位置来确定节点在网络中传播内容的效率。利用SIR(易感感染-恢复)模型评价CSE策略的性能。结果证明了CSE策略在微信网络中选择重要节点传播内容的有效性。
{"title":"CSE: A Content Spreading Efficiency Based Influential Nodes Selection Method in 5G Mobile Social Networks","authors":"M. M. Tulu, Sultan Feisso, Ronghui Hou, Talha Younas","doi":"10.1109/ICICT50521.2020.00082","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00082","url":null,"abstract":"Mobile Social Network (MSN) is attracting the attention of many researchers so as to leverage cellular links by offloading the mobile traffic load via device-to-device communications. Therefore, applying an effective algorithm to identify influential spreaders in MSN is playing a key role. In this paper, a Content Spreading Efficiency (CSE) algorithm, which considers the degree and the number of contact times of a node with its neighbors and the neighbors' friends, is proposed. Also, it considers the nodes' topological position to determine the efficiency of the node to spread content in the network. The performance of CSE strategy is evaluated by Susceptible Infected-Recovered (SIR) model. The results demonstrate the effectiveness of CSE strategy to select important nodes to spread content in MSNs.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123601026","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00057
Qianhao Zhai, Yang Deng, H. Zhou, Siling Feng, Mengxing Huang
How should taxi drivers make decisions to maximize profits? This is a matter of concern. Profit efficiency of taxi drivers is evaluated based on the method of qualitative analysis in this paper. Taking profit, cost and time as the relevant factors of decision making, the mathematical model of profit efficiency is established, and the profit efficiency is calculated when the taxi driver chooses two different schemes. The preferable scheme is recommended to the driver. The real data were collected and plugged into the model to verify the reasonability of the model. Correlation analysis in SPSS was used to calculate partial correlation coefficient to measure the model's dependency on relevant factors. The results show that the model in the paper is effective and can be used to instruct the taxi driver to make decisions.
{"title":"A Decision Model of Taxi Driver Based on Qualitative Analysis","authors":"Qianhao Zhai, Yang Deng, H. Zhou, Siling Feng, Mengxing Huang","doi":"10.1109/ICICT50521.2020.00057","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00057","url":null,"abstract":"How should taxi drivers make decisions to maximize profits? This is a matter of concern. Profit efficiency of taxi drivers is evaluated based on the method of qualitative analysis in this paper. Taking profit, cost and time as the relevant factors of decision making, the mathematical model of profit efficiency is established, and the profit efficiency is calculated when the taxi driver chooses two different schemes. The preferable scheme is recommended to the driver. The real data were collected and plugged into the model to verify the reasonability of the model. Correlation analysis in SPSS was used to calculate partial correlation coefficient to measure the model's dependency on relevant factors. The results show that the model in the paper is effective and can be used to instruct the taxi driver to make decisions.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116508747","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00040
F. Sanfilippo, C. Pacchierotti
Haptic technology for human augmentation provides gains in ability for different applications, whether the aim is to enhance "disabilities" to "abilities", or "abilities" to "super-abilities". Commercially-available devices are generally expensive and tailored to specific applications and hardware. To give researchers a haptic feedback system that is economical, customisable, and fast to fabricate, our group developed a low-cost immersive haptic, audio, and visual experience built by using off-the-shelf (COTS) components. It is composed of a vibrotactile glove, a Leap Motion sensor, and an head-mounted display, integrated together to provide compelling immersive sensations. This paper proposes a higher technology readiness level (TRL) for the system to make it modular and reliable. To demonstrate its potential, we present two human subject studies in Virtual Reality. They evaluate the capability of the system in providing (i) guidance during simulated drone operations, and (ii) contact haptic feedback during virtual objects interaction. Results prove that the proposed haptic-enabled framework improves the performance and illusion of presence.
{"title":"A Low-Cost Multi-modal Auditory-Visual-Tactile Framework for Remote Touch","authors":"F. Sanfilippo, C. Pacchierotti","doi":"10.1109/ICICT50521.2020.00040","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00040","url":null,"abstract":"Haptic technology for human augmentation provides gains in ability for different applications, whether the aim is to enhance \"disabilities\" to \"abilities\", or \"abilities\" to \"super-abilities\". Commercially-available devices are generally expensive and tailored to specific applications and hardware. To give researchers a haptic feedback system that is economical, customisable, and fast to fabricate, our group developed a low-cost immersive haptic, audio, and visual experience built by using off-the-shelf (COTS) components. It is composed of a vibrotactile glove, a Leap Motion sensor, and an head-mounted display, integrated together to provide compelling immersive sensations. This paper proposes a higher technology readiness level (TRL) for the system to make it modular and reliable. To demonstrate its potential, we present two human subject studies in Virtual Reality. They evaluate the capability of the system in providing (i) guidance during simulated drone operations, and (ii) contact haptic feedback during virtual objects interaction. Results prove that the proposed haptic-enabled framework improves the performance and illusion of presence.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124842095","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00094
Sriveni Namani, Bilal Gonen
The improvement in new technologies in this modern era has resulted to miniaturization of sensors and the attempts to utilize them in various areas are getting succeeded. Also, adoption of Internet of Things (IoT) and Cloud Computing in any area are leading them to a notion of "Smart" like Smart Health Care systems, Smart Cities, Smart Mobility, Smart Grid, Smart Home and Smart Metering etc. One such area of research that has also seen this adoption is agriculture and thus making it a Smart Agriculture. Agriculture is one of the major source for any of the largest population countries like India, China etc. to earn money and carry out the livelihood. Involvement of IoT and Cloud Computing in the agricultural sector would result in the better production of crops by controlling the cost, monitoring performance and maintenance, thereby benefiting the farmers and the overall nation. This paper focuses on introduction of a Smart Drone for crop management where the real-time Drone data coupled with IoT and Cloud Computing technologies help in building a sustainable Smart Agriculture.
{"title":"Smart Agriculture Based on IoT and Cloud Computing","authors":"Sriveni Namani, Bilal Gonen","doi":"10.1109/ICICT50521.2020.00094","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00094","url":null,"abstract":"The improvement in new technologies in this modern era has resulted to miniaturization of sensors and the attempts to utilize them in various areas are getting succeeded. Also, adoption of Internet of Things (IoT) and Cloud Computing in any area are leading them to a notion of \"Smart\" like Smart Health Care systems, Smart Cities, Smart Mobility, Smart Grid, Smart Home and Smart Metering etc. One such area of research that has also seen this adoption is agriculture and thus making it a Smart Agriculture. Agriculture is one of the major source for any of the largest population countries like India, China etc. to earn money and carry out the livelihood. Involvement of IoT and Cloud Computing in the agricultural sector would result in the better production of crops by controlling the cost, monitoring performance and maintenance, thereby benefiting the farmers and the overall nation. This paper focuses on introduction of a Smart Drone for crop management where the real-time Drone data coupled with IoT and Cloud Computing technologies help in building a sustainable Smart Agriculture.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123980594","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00016
Amjed Al-Thuhli, Mohammed Al-Badawi
The involvement of human interactions with business processes through Enterprise Social Networks improves organizations performance. However, Enterprise Social Networks consist of massive amount of data in form of structure and unstructured data. Therefore, finding valuable information from these types of data is a challenging issue. Nevertheless, with the annotation that are available in form of social tagging, some challenges have been resolved. In this paper, we investigate the problem of using social tagging in order to socialize organization business processes. Specifically, we present a framework to analyze social tagging and unstructured data that are generated by users to recommend tasks and activities of any type of business processes based on hybrid method of clustering and text classification. The framework uses k-means algorithm to cluster tags datasets and term frequency–inverse document frequency to weight user's documents. The experiment results performed on a real case study shows the efficiency of the framework after validates its accuracy.
{"title":"A Framework to Analyze Social Tagging and Unstructured Data","authors":"Amjed Al-Thuhli, Mohammed Al-Badawi","doi":"10.1109/ICICT50521.2020.00016","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00016","url":null,"abstract":"The involvement of human interactions with business processes through Enterprise Social Networks improves organizations performance. However, Enterprise Social Networks consist of massive amount of data in form of structure and unstructured data. Therefore, finding valuable information from these types of data is a challenging issue. Nevertheless, with the annotation that are available in form of social tagging, some challenges have been resolved. In this paper, we investigate the problem of using social tagging in order to socialize organization business processes. Specifically, we present a framework to analyze social tagging and unstructured data that are generated by users to recommend tasks and activities of any type of business processes based on hybrid method of clustering and text classification. The framework uses k-means algorithm to cluster tags datasets and term frequency–inverse document frequency to weight user's documents. The experiment results performed on a real case study shows the efficiency of the framework after validates its accuracy.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117041420","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00030
T. Mapayi, P. Owolawi
As digital retina imaging and automatic retinal vascular network analysis continue to find increasing usefulness in the field of biomedicine for the diagnosis, monitoring and management of various forms of human illness like hypertension, retinopathies, glaucoma and cardiovascular diseases, the mitigation of different complications such as nonhomogeneous illumination noise, vessel width variation and very low contrast of the small-width vessels in relation to the retinal fundus background, for an efficient segmentation performance remains a subject of on-going research. This paper investigates the use of an adaptive thresholding method based on local spatial relational variance (LSRV) for the segmentation of the retinal vascular networks in fundus images. An experimental study conducted on DRIVE database shows that the vascular network segmentation results obtained from the investigated method detects large vessels and thin vessels in the retinal fundus images. When compared to some previous methods in the literature, the proposed method achieved higher average accuracy value of 95.04% and average sensitivity value of 76.55%. The proposed method is also computationally fast with a processing time of 4.5 seconds for the segmentation of the retinal vascular networks in each fundus image.
{"title":"Retinal Vascular Network Segmentation Using Adaptive Thresholding Method Based on LSRV","authors":"T. Mapayi, P. Owolawi","doi":"10.1109/ICICT50521.2020.00030","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00030","url":null,"abstract":"As digital retina imaging and automatic retinal vascular network analysis continue to find increasing usefulness in the field of biomedicine for the diagnosis, monitoring and management of various forms of human illness like hypertension, retinopathies, glaucoma and cardiovascular diseases, the mitigation of different complications such as nonhomogeneous illumination noise, vessel width variation and very low contrast of the small-width vessels in relation to the retinal fundus background, for an efficient segmentation performance remains a subject of on-going research. This paper investigates the use of an adaptive thresholding method based on local spatial relational variance (LSRV) for the segmentation of the retinal vascular networks in fundus images. An experimental study conducted on DRIVE database shows that the vascular network segmentation results obtained from the investigated method detects large vessels and thin vessels in the retinal fundus images. When compared to some previous methods in the literature, the proposed method achieved higher average accuracy value of 95.04% and average sensitivity value of 76.55%. The proposed method is also computationally fast with a processing time of 4.5 seconds for the segmentation of the retinal vascular networks in each fundus image.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128302444","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}
Pub Date : 2020-03-01DOI: 10.1109/ICICT50521.2020.00045
Zhang Chunyong, Xiaojing Meng
System logs are often used as the primary resource in data-driven methods to ensure system health and stability. The typical process of system log analysis is to first parse unstructured logs into structured data, and then apply data mining and machine learning techniques to analyze the data and build a workflow model. Existing log parsing methods focus on similar matching of log messages and log templates. We believe that the accuracy of log message parsing is the primary task of log parsing, so we propose One-to-One, a log parser that is marked one-to-one according to the rules duringthe matching process according to the token type and part of speech. Way to parse log messages online. We evaluated Oneto-One on different log sets and compared them with the three most advanced log parsing methods. The results show that our method is similar to the results of the other three methods in parsing simple logs. However, when parsing complex OpenStack logs, the accuracy can reach 98%, which is 20% higher than the best. It can parse tens of thousands of log messages per second. This method shows high efficiency and precision for all three types of test logs, and is applicable to modern system logs.
{"title":"Log Parser with One-to-One Markup","authors":"Zhang Chunyong, Xiaojing Meng","doi":"10.1109/ICICT50521.2020.00045","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00045","url":null,"abstract":"System logs are often used as the primary resource in data-driven methods to ensure system health and stability. The typical process of system log analysis is to first parse unstructured logs into structured data, and then apply data mining and machine learning techniques to analyze the data and build a workflow model. Existing log parsing methods focus on similar matching of log messages and log templates. We believe that the accuracy of log message parsing is the primary task of log parsing, so we propose One-to-One, a log parser that is marked one-to-one according to the rules duringthe matching process according to the token type and part of speech. Way to parse log messages online. We evaluated Oneto-One on different log sets and compared them with the three most advanced log parsing methods. The results show that our method is similar to the results of the other three methods in parsing simple logs. However, when parsing complex OpenStack logs, the accuracy can reach 98%, which is 20% higher than the best. It can parse tens of thousands of log messages per second. This method shows high efficiency and precision for all three types of test logs, and is applicable to modern system logs.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130723354","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：