Pub Date : 2021-09-13DOI: 10.18690/978-961-286-516-0.5
Arunita Das, Daipayan Ghosal, Krishna Gopal Dhal
Segmentation of Plant Images plays an important role in modern agriculture where it can provide accurate analysis of a plant’s growth and possi-ble anomalies. In this paper, rough set based partitional clustering technique called Rough K-Means has been utilized in CIELab color space for the proper leaf segmentation of rosette plants. The eÿcacy of the proposed technique have been analysed by comparing it with the results of tra-ditional K-Means and Fuzzy C-Means clustering algorithms. The visual and numerical results re-veal that the RKM in CIELab provides the near-est result to the ideal ground truth, hence the most eÿcient one.
{"title":"Leaf Segmentation of Rosette Plants using Rough K-Means in CIELab Color Space","authors":"Arunita Das, Daipayan Ghosal, Krishna Gopal Dhal","doi":"10.18690/978-961-286-516-0.5","DOIUrl":"https://doi.org/10.18690/978-961-286-516-0.5","url":null,"abstract":"Segmentation of Plant Images plays an important role in modern agriculture where it can provide accurate analysis of a plant’s growth and possi-ble anomalies. In this paper, rough set based partitional clustering technique called Rough K-Means has been utilized in CIELab color space for the proper leaf segmentation of rosette plants. The eÿcacy of the proposed technique have been analysed by comparing it with the results of tra-ditional K-Means and Fuzzy C-Means clustering algorithms. The visual and numerical results re-veal that the RKM in CIELab provides the near-est result to the ideal ground truth, hence the most eÿcient one.","PeriodicalId":282591,"journal":{"name":"Proceedings of the 2021 7th Student Computer Science Research Conference (StuCoSReC)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114089713","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 : 2021-09-13DOI: 10.18690/978-961-286-516-0.16
Uroš Zagoranski
V prispevku smo se osredotočili na časovne razpo-rejevalnike (ang. cron job schedulers) v brezstre-žniškem (ang. serverless) okolju in njihovo zane-sljivo uporabo. Primerjali smo razporejevalnike, implementirane s pomočjo zabojnikov s tistimi, ki so gostovani v oblaku z uporabo pristopa funk-cije kot storitve. Ugotavljali smo, katere so po-sebnosti časovnih razporejevalnikov v brezstrežni-škem okolju in kdaj je le-te sploh smiselno upo-rabiti. Na praktičnem primeru smo predstavili, kako jih lahko vključimo v večji sistem in na ka-kšen način najlažje rešimo morebitne težave, ki jih ob izbiri brezstrežniškega okolja zavestno pre-vzamemo. Ugotovili smo, da so razporejevalniki v FaaS (ang. Function as a Service) okolju naj-primernejši zaradi enostavnega in hitrega razvoja ter nizkih stroškov obratovanja.
{"title":"Časovni razporejevalniki in brezstrežniško okolje","authors":"Uroš Zagoranski","doi":"10.18690/978-961-286-516-0.16","DOIUrl":"https://doi.org/10.18690/978-961-286-516-0.16","url":null,"abstract":"V prispevku smo se osredotočili na časovne razpo-rejevalnike (ang. cron job schedulers) v brezstre-žniškem (ang. serverless) okolju in njihovo zane-sljivo uporabo. Primerjali smo razporejevalnike, implementirane s pomočjo zabojnikov s tistimi, ki so gostovani v oblaku z uporabo pristopa funk-cije kot storitve. Ugotavljali smo, katere so po-sebnosti časovnih razporejevalnikov v brezstrežni-škem okolju in kdaj je le-te sploh smiselno upo-rabiti. Na praktičnem primeru smo predstavili, kako jih lahko vključimo v večji sistem in na ka-kšen način najlažje rešimo morebitne težave, ki jih ob izbiri brezstrežniškega okolja zavestno pre-vzamemo. Ugotovili smo, da so razporejevalniki v FaaS (ang. Function as a Service) okolju naj-primernejši zaradi enostavnega in hitrega razvoja ter nizkih stroškov obratovanja.","PeriodicalId":282591,"journal":{"name":"Proceedings of the 2021 7th Student Computer Science Research Conference (StuCoSReC)","volume":"vmr-4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127931055","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 : 2021-09-13DOI: 10.18690/978-961-286-516-0.10
Matic Rašl, Mitja Zalik, Vid Keršič
Sarcasm detection is an important problem in the field of natural language processing. In this pa-per, we compare performances of the three neural networks for sarcasm detection on English and Slovene datasets. Each network is based on a di˙erent transformer model: RoBERTa, Distil-Bert, and DistilBert – multilingual. In addition to the existing Twitter-based English dataset, we also created the Slovene dataset using the same approach. An F1 score of 0.72 and 0.88 was achieved in the English and Slovene dataset, re-spectively.
{"title":"Transformer-based Sarcasm Detection in English and Slovene Language","authors":"Matic Rašl, Mitja Zalik, Vid Keršič","doi":"10.18690/978-961-286-516-0.10","DOIUrl":"https://doi.org/10.18690/978-961-286-516-0.10","url":null,"abstract":"Sarcasm detection is an important problem in the field of natural language processing. In this pa-per, we compare performances of the three neural networks for sarcasm detection on English and Slovene datasets. Each network is based on a di˙erent transformer model: RoBERTa, Distil-Bert, and DistilBert – multilingual. In addition to the existing Twitter-based English dataset, we also created the Slovene dataset using the same approach. An F1 score of 0.72 and 0.88 was achieved in the English and Slovene dataset, re-spectively.","PeriodicalId":282591,"journal":{"name":"Proceedings of the 2021 7th Student Computer Science Research Conference (StuCoSReC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129785418","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：