Analyzing the secondary wastewater-treatment process using Faster R-CNN and YOLOv5 object detection algorithms
The activated sludge (AS) process is the most common type of secondary wastewater treatment, applied worldwide. Due to the complexity of microbial communities, imbalances between the different types of bacteria may occur and disturb the process, with pronounced economical and environmental consequen...
Gespeichert in:
| Veröffentlicht in: | Journal of cleaner production Jg. 416; S. 137913 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier Ltd
01.09.2023
|
| Schlagworte: | |
| ISSN: | 0959-6526, 1879-1786 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | The activated sludge (AS) process is the most common type of secondary wastewater treatment, applied worldwide. Due to the complexity of microbial communities, imbalances between the different types of bacteria may occur and disturb the process, with pronounced economical and environmental consequences. Microscopic inspection of the morphology of flocs and microorganisms provides key information on AS properties and function. This is a time-consuming, highly skilled, and expensive process that is not readily available in all locations. Thus, most wastewater-treatment plants do not carry out this essential analysis, resulting in frequent operational faults. In this study, we develop a novel deep learning (DL) object detection algorithm to analyze and monitor the AS process based on a unique microscopic image database of flocs and microorganisms. Specifically, we applied YOLOv5 and Faster R-CNN algorithms as tools for segmentation and object detection to analyze the wastewater. The mean average precision (mAP) of the YOLOv5 was 0.67, outperforming the Faster R-CNN by 15%. Histogram equalization preprocessing of both bright-field and phase-contrast images significantly improved the results of the algorithm in all classes. In the case of YOLOv5, the mAP increased by 16.67%, to 0.77, where the AP of protozoa, filaments, and open floc classes outperformed the previous model by over 20%. These results demonstrate the potential of leveraging DL algorithms to enhance the analysis and monitoring of WWTPs in an affordable manner, consequently reducing environmental pollution caused by contaminated effluent. The fundamental challenge addressed herein has important global relevance, especially in an era in which the demand for high-quality wastewater reuse is expected to increase dramatically.
[Display omitted]
•Deep learning object detection algorithms for secondary treatment are proposed.•Mean average precision of YOLOv5 was 0.67, outperforming Faster R-CNN by 15%.•Histogram equalization significantly improved mAP of YOLOv5 by 16.67% to 0.77•Unique microscopic image database from Israeli WWTPs was used.•This framework can be adopted by WWTPs to manage secondary treatment process. |
|---|---|
| AbstractList | The activated sludge (AS) process is the most common type of secondary wastewater treatment, applied worldwide. Due to the complexity of microbial communities, imbalances between the different types of bacteria may occur and disturb the process, with pronounced economical and environmental consequences. Microscopic inspection of the morphology of flocs and microorganisms provides key information on AS properties and function. This is a time-consuming, highly skilled, and expensive process that is not readily available in all locations. Thus, most wastewater-treatment plants do not carry out this essential analysis, resulting in frequent operational faults. In this study, we develop a novel deep learning (DL) object detection algorithm to analyze and monitor the AS process based on a unique microscopic image database of flocs and microorganisms. Specifically, we applied YOLOv5 and Faster R-CNN algorithms as tools for segmentation and object detection to analyze the wastewater. The mean average precision (mAP) of the YOLOv5 was 0.67, outperforming the Faster R-CNN by 15%. Histogram equalization preprocessing of both bright-field and phase-contrast images significantly improved the results of the algorithm in all classes. In the case of YOLOv5, the mAP increased by 16.67%, to 0.77, where the AP of protozoa, filaments, and open floc classes outperformed the previous model by over 20%. These results demonstrate the potential of leveraging DL algorithms to enhance the analysis and monitoring of WWTPs in an affordable manner, consequently reducing environmental pollution caused by contaminated effluent. The fundamental challenge addressed herein has important global relevance, especially in an era in which the demand for high-quality wastewater reuse is expected to increase dramatically.
[Display omitted]
•Deep learning object detection algorithms for secondary treatment are proposed.•Mean average precision of YOLOv5 was 0.67, outperforming Faster R-CNN by 15%.•Histogram equalization significantly improved mAP of YOLOv5 by 16.67% to 0.77•Unique microscopic image database from Israeli WWTPs was used.•This framework can be adopted by WWTPs to manage secondary treatment process. The activated sludge (AS) process is the most common type of secondary wastewater treatment, applied worldwide. Due to the complexity of microbial communities, imbalances between the different types of bacteria may occur and disturb the process, with pronounced economical and environmental consequences. Microscopic inspection of the morphology of flocs and microorganisms provides key information on AS properties and function. This is a time-consuming, highly skilled, and expensive process that is not readily available in all locations. Thus, most wastewater-treatment plants do not carry out this essential analysis, resulting in frequent operational faults. In this study, we develop a novel deep learning (DL) object detection algorithm to analyze and monitor the AS process based on a unique microscopic image database of flocs and microorganisms. Specifically, we applied YOLOv5 and Faster R-CNN algorithms as tools for segmentation and object detection to analyze the wastewater. The mean average precision (mAP) of the YOLOv5 was 0.67, outperforming the Faster R-CNN by 15%. Histogram equalization preprocessing of both bright-field and phase-contrast images significantly improved the results of the algorithm in all classes. In the case of YOLOv5, the mAP increased by 16.67%, to 0.77, where the AP of protozoa, filaments, and open floc classes outperformed the previous model by over 20%. These results demonstrate the potential of leveraging DL algorithms to enhance the analysis and monitoring of WWTPs in an affordable manner, consequently reducing environmental pollution caused by contaminated effluent. The fundamental challenge addressed herein has important global relevance, especially in an era in which the demand for high-quality wastewater reuse is expected to increase dramatically. |
| ArticleNumber | 137913 |
| Author | Shahar, Moni Inbar, Offir Menashe, Ofir Gidron, Jacob Avisar, Dror Cohen, Ido |
| Author_xml | – sequence: 1 givenname: Offir surname: Inbar fullname: Inbar, Offir organization: The Water Research Center, Porter School of the Environment and Earth Sciences, Faculty of Exact Sciences, Tel Aviv University, Tel Aviv, Israel – sequence: 2 givenname: Moni orcidid: 0000-0001-7512-9640 surname: Shahar fullname: Shahar, Moni organization: TAD – Center for Artificial Intelligence & Data Science, Tel Aviv University, Tel Aviv, Israel – sequence: 3 givenname: Jacob surname: Gidron fullname: Gidron, Jacob organization: School of Computer Science, Faculty of Exact Sciences, Tel Aviv University, Tel Aviv, Israel – sequence: 4 givenname: Ido orcidid: 0009-0008-9187-0840 surname: Cohen fullname: Cohen, Ido organization: School of Computer Science, Faculty of Exact Sciences, Tel Aviv University, Tel Aviv, Israel – sequence: 5 givenname: Ofir orcidid: 0000-0001-7368-0754 surname: Menashe fullname: Menashe, Ofir organization: Water Industry Engineering Department, The Engineering Faculty, Kinneret Academic College on the Sea of Galilee, M.P. Emek Ha'Yarden, Israel – sequence: 6 givenname: Dror orcidid: 0000-0001-9199-1548 surname: Avisar fullname: Avisar, Dror email: droravi@tauex.tau.ac.il organization: The Water Research Center, Porter School of the Environment and Earth Sciences, Faculty of Exact Sciences, Tel Aviv University, Tel Aviv, Israel |
| BookMark | eNqFkEtLxDAUhYMoOD5-gpClm45J0zYNLkQGXzA4IG5chTS51ZROoklGGX-9KePKjauzOd-5l-8I7TvvAKEzSuaU0OZimA96hPfg5yUp2ZwyLijbQzPaclFQ3jb7aEZELYqmLptDdBTjQAjlhFcz5K6dGrff1r3i9AY4gvbOqLDFXyom-FIJQpECqLQGl3C-oSFGvIkTcDtVAn4qFo-PWDmDX1bL1WeNfTeATthAymG9w2p89cGmt3U8QQe9GiOc_uYxer69eV7cF8vV3cPielloVpWpMIbUHW37qlG6aioiGtUp6KmirGqNFrTiHemgBuhNxWrSl43uWiUE15y2NTtG57vZ_PDHBmKSaxs1jKNy4DdRlqLMqgRnLFcvd1UdfIwBeqltUtPbKSg7SkrkJFkO8leynCTLneRM13_o92DX2d-_3NWOgyzh00KQUVtwGowNWZo03v6z8ANFyp3n |
| CitedBy_id | crossref_primary_10_1016_j_jwpe_2025_108513 crossref_primary_10_1016_j_compind_2024_104154 crossref_primary_10_1038_s41598_025_93954_x crossref_primary_10_3390_info15010011 crossref_primary_10_1016_j_jwpe_2025_108457 crossref_primary_10_1016_j_marpetgeo_2024_106965 crossref_primary_10_1111_jmi_13385 crossref_primary_10_1016_j_jenvman_2025_127008 crossref_primary_10_3390_w16182680 crossref_primary_10_3390_electronics13193840 crossref_primary_10_1002_advs_202406912 crossref_primary_10_1016_j_scitotenv_2024_175813 crossref_primary_10_1007_s11042_025_20750_0 crossref_primary_10_1080_10402004_2024_2449503 crossref_primary_10_1016_j_compchemeng_2024_108791 crossref_primary_10_1016_j_envres_2025_120822 crossref_primary_10_1016_j_jclepro_2024_140573 crossref_primary_10_1016_j_jwpe_2024_105212 crossref_primary_10_1016_j_landurbplan_2024_105204 crossref_primary_10_1016_j_compag_2025_110277 crossref_primary_10_3390_pr12061054 crossref_primary_10_1016_j_jenvman_2025_126886 crossref_primary_10_1016_j_jenvman_2024_122386 crossref_primary_10_1088_1361_6501_adf657 crossref_primary_10_1039_D4EW00111G crossref_primary_10_1109_ACCESS_2024_3477967 |
| Cites_doi | 10.1016/j.scitotenv.2022.154930 10.1016/j.watres.2017.06.063 10.1016/j.watres.2004.03.007 10.1515/aep-2017-0042 10.1016/0043-1354(94)90120-1 10.1016/j.jece.2022.107430 10.1007/978-94-011-3951-9_10 10.1016/j.chemosphere.2019.02.088 10.1007/s12355-018-0633-z 10.1016/j.aca.2013.09.016 10.1016/j.desal.2004.06.113 10.1109/30.754419 10.1016/j.dsp.2003.07.002 10.1093/eurheartj/ehy404 10.1007/s11831-020-09425-1 10.3390/w14081275 10.1016/j.psep.2019.11.014 10.1016/j.watres.2007.01.011 10.1016/j.cej.2010.07.061 10.1016/j.watres.2007.12.013 10.3390/electronics10141711 10.1007/978-981-13-9042-5_56 10.1109/TNNLS.2018.2876865 10.1016/0043-1354(94)00326-3 10.1016/j.scitotenv.2022.153311 10.2166/wst.2018.189 10.1016/j.jwpe.2014.12.009 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.jclepro.2023.137913 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1879-1786 |
| ExternalDocumentID | 10_1016_j_jclepro_2023_137913 S0959652623020711 |
| GroupedDBID | --K --M ..I .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AAEDT AAEDW AAHCO AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AARJD AAXUO ABFYP ABJNI ABLST ABMAC ABYKQ ACDAQ ACGFS ACRLP ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHHHB AHIDL AIEXJ AIKHN AITUG AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BELTK BKOJK BLECG BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W JARJE K-O KCYFY KOM LY9 M41 MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RNS ROL RPZ SCC SDF SDG SDP SES SEW SPC SPCBC SSJ SSR SSZ T5K ~G- 29K 9DU AAHBH AAQXK AATTM AAXKI AAYWO AAYXX ABFNM ABWVN ABXDB ACLOT ACRPL ACVFH ADCNI ADHUB ADMUD ADNMO AEGFY AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION D-I EFKBS EJD FEDTE FGOYB G-2 HMC HVGLF HZ~ R2- SEN WUQ ZY4 ~HD 7S9 L.6 |
| ID | FETCH-LOGICAL-c342t-dd05b18f46ac464096abaef1a1348dc9147b0be5eefd4350f26cb8a997c71853 |
| ISICitedReferencesCount | 25 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001036439000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0959-6526 |
| IngestDate | Wed Oct 01 14:56:04 EDT 2025 Sat Nov 29 07:07:06 EST 2025 Tue Nov 18 20:15:46 EST 2025 Fri Feb 23 02:36:46 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Computer vision Activated sludge Secondary treatment Wastewater Water quality |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c342t-dd05b18f46ac464096abaef1a1348dc9147b0be5eefd4350f26cb8a997c71853 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0001-9199-1548 0009-0008-9187-0840 0000-0001-7368-0754 0000-0001-7512-9640 |
| PQID | 2922029733 |
| PQPubID | 24069 |
| ParticipantIDs | proquest_miscellaneous_2922029733 crossref_citationtrail_10_1016_j_jclepro_2023_137913 crossref_primary_10_1016_j_jclepro_2023_137913 elsevier_sciencedirect_doi_10_1016_j_jclepro_2023_137913 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-09-01 2023-09-00 20230901 |
| PublicationDateYYYYMMDD | 2023-09-01 |
| PublicationDate_xml | – month: 09 year: 2023 text: 2023-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of cleaner production |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Ly, Truong, Ji, Nguyen, Cho, Ngo, Zhang (bib24) 2022; 832 Yao, Qi, Zhang, Shao, Yang, Li (bib43) 2021; 10 Jocher, Stoken, Borovec, NanoCode012, ChristopherSTAN, Changyu, Laughing, tkianai, yx, Hogan, lorenzomammana, Chaurasia, Diaconu, Marc, haoyang0106, ml5ah, Doug, Ingham, Frederik, Colmagro, Ye, Jacobsolawetz, Poznanski, Fang, Kim, Doan, 于力军 (bib18) 2021 Eikelboom (bib13) 2000 Salvadó, Palomo, Mas, Puigagut, Gracia (bib36) 2004; 38 Madoni (bib25) 1994; 28 Girshick (bib15) 2015 Zaghloul, Achari (bib44) 2022; 10 Madoni (bib26) 2010 Sonune, Ghate (bib38) 2004; 167 Dhal, Das, Ray, Gálvez, Das (bib12) 2021; 28 Burger, Krysiak-Baltyn, Scales, Martin, Stickland, Gras (bib6) 2017; 123 Park, Baek, Kim, You, Kim (bib30) 2022; 14 Wu, Kirillov, Massa, Lo, Girshick (bib42) 2019 Schuler, Jang (bib37) 2007; 41 Johnston, LaPara, Behrens (bib19) 2019; 9 Wang, Chen, Zhang (bib39) 1999; 45 Al'Aref, Anchouche, Singh, Slomka, Kolli, Kumar, Pandey, Maliakal, van Rosendael, Beecy, Berman, Leipsic, Nieman, Andreini, Pontone, Schoepf, Shaw, Chang, Narula, Bax, Guan, Min (bib2) 2019; 40 Prasad, Venkataramana, Kumar, Prasannamedha, Harshana, Srividya, Harrinei, Indraganti (bib32) 2022; 821 Gnida (bib16) 2017; 43 Lindrea, Seviour, Seviour, Blackall, Soddell (bib23) 1998 Deng, Dong, Socher, Li, Li, Fei-Fei (bib10) 2010 Minaee, Boykov, Porikli, Plaza, Kehtarnavaz, Terzopoulos (bib28) 2022; 44 (bib41) 2022 Rolnick, Donti, Kaack, Kochanski, Lacoste, Sankaran, Ross, Milojevic-Dupont, Jaques, Waldman-Brown, Luccioni, Maharaj, Sherwin, Mukkavilli, Kording, Gomes, Ng, Hassabis, Platt, Creutzig, Chayes, Bengio (bib35) 2019 Kim, Sung, Park (bib21) 2020 Wilén, Onuki, Hermansson, Lumley, Mino (bib40) 2008; 42 Zhao, Zheng, Xu, Wu (bib45) 2019; 30 Jones, Schuler (bib20) 2010; 164 Roboflow (bib34) Albawi, Mohammed, Al-Zawi (bib1) 2018 Redmon, Divvala, Girshick, Farhadi (bib33) 2016 Zhou, Zhao, Nie (bib47) 2021 Fito, Tefera, Kloos, Van Hulle (bib14) 2019; 21 Koivuranta, Stoor, Hattuniemi, Niinimäki (bib22) 2015; 5 Campbell, Wang, Daniels (bib7) 2019; 223 Cheng, Shi (bib9) 2004; 14 bib17 Mesquita, Amaral, Ferreira (bib27) 2013; 802 Boretti, Rosa (bib5) 2019 Perez, Wang (bib31) 2017 Oliveira, Alliet, Coufort-Saudejaud, Frances (bib29) 2018; 77 Bharati, Pramanik (bib4) 2020; 999 Zhao, Dai, Qiao, Sun, Hao, Yang (bib46) 2020; 133 Chauhan, Ghanshala, Joshi (bib8) 2018 Barbusiński, Kościelniak (bib3) 1995; 29 Deshpande, Singh, Herunde (bib11) 2020; 9 Madoni (10.1016/j.jclepro.2023.137913_bib25) 1994; 28 Gnida (10.1016/j.jclepro.2023.137913_bib16) 2017; 43 Boretti (10.1016/j.jclepro.2023.137913_bib5) Zhou (10.1016/j.jclepro.2023.137913_bib47) 2021 Deng (10.1016/j.jclepro.2023.137913_bib10) Johnston (10.1016/j.jclepro.2023.137913_bib19) 2019; 9 Oliveira (10.1016/j.jclepro.2023.137913_bib29) 2018; 77 Lindrea (10.1016/j.jclepro.2023.137913_bib23) 1998 Chauhan (10.1016/j.jclepro.2023.137913_bib8) 2018 Yao (10.1016/j.jclepro.2023.137913_bib43) 2021; 10 Zhao (10.1016/j.jclepro.2023.137913_bib46) 2020; 133 Fito (10.1016/j.jclepro.2023.137913_bib14) 2019; 21 Ly (10.1016/j.jclepro.2023.137913_bib24) 2022; 832 Dhal (10.1016/j.jclepro.2023.137913_bib12) 2021; 28 Mesquita (10.1016/j.jclepro.2023.137913_bib27) 2013; 802 Campbell (10.1016/j.jclepro.2023.137913_bib7) 2019; 223 Albawi (10.1016/j.jclepro.2023.137913_bib1) 2018 Prasad (10.1016/j.jclepro.2023.137913_bib32) 2022; 821 Schuler (10.1016/j.jclepro.2023.137913_bib37) 2007; 41 Jocher (10.1016/j.jclepro.2023.137913_bib18) 2021 Deshpande (10.1016/j.jclepro.2023.137913_bib11) 2020; 9 Minaee (10.1016/j.jclepro.2023.137913_bib28) 2022; 44 Al'Aref (10.1016/j.jclepro.2023.137913_bib2) 2019; 40 Jones (10.1016/j.jclepro.2023.137913_bib20) 2010; 164 Eikelboom (10.1016/j.jclepro.2023.137913_bib13) 2000 Girshick (10.1016/j.jclepro.2023.137913_bib15) 2015 (10.1016/j.jclepro.2023.137913_bib41) 2022 Wu (10.1016/j.jclepro.2023.137913_bib42) Cheng (10.1016/j.jclepro.2023.137913_bib9) 2004; 14 Roboflow (10.1016/j.jclepro.2023.137913_bib34) Zaghloul (10.1016/j.jclepro.2023.137913_bib44) 2022; 10 Sonune (10.1016/j.jclepro.2023.137913_bib38) 2004; 167 Perez (10.1016/j.jclepro.2023.137913_bib31) Barbusiński (10.1016/j.jclepro.2023.137913_bib3) 1995; 29 Kim (10.1016/j.jclepro.2023.137913_bib21) 2020 Rolnick (10.1016/j.jclepro.2023.137913_bib35) 2019 Salvadó (10.1016/j.jclepro.2023.137913_bib36) 2004; 38 Zhao (10.1016/j.jclepro.2023.137913_bib45) 2019; 30 Madoni (10.1016/j.jclepro.2023.137913_bib26) Bharati (10.1016/j.jclepro.2023.137913_bib4) 2020; 999 Wang (10.1016/j.jclepro.2023.137913_bib39) 1999; 45 Wilén (10.1016/j.jclepro.2023.137913_bib40) 2008; 42 Burger (10.1016/j.jclepro.2023.137913_bib6) 2017; 123 Redmon (10.1016/j.jclepro.2023.137913_bib33) 2016 Koivuranta (10.1016/j.jclepro.2023.137913_bib22) 2015; 5 Park (10.1016/j.jclepro.2023.137913_bib30) 2022; 14 |
| References_xml | – ident: bib17 – volume: 14 start-page: 1275 year: 2022 ident: bib30 article-title: Deep learning-based algal detection model development considering field application publication-title: Water – volume: 42 start-page: 2300 year: 2008 end-page: 2308 ident: bib40 article-title: Microbial community structure in activated sludge floc analysed by fluorescence in situ hybridization and its relation to floc stability publication-title: Water Res. – volume: 123 start-page: 578 year: 2017 end-page: 585 ident: bib6 article-title: The influence of protruding filamentous bacteria on floc stability and solid-liquid separation in the activated sludge process publication-title: Water Res. – volume: 43 start-page: 66 year: 2017 end-page: 71 ident: bib16 article-title: Use of DAIME for characterisation of activated sludge flocs publication-title: Arch. Environ. Protect. – year: 2019 ident: bib5 article-title: Reassessing the projections of the world water development report – volume: 9 start-page: 1 year: 2019 end-page: 15 ident: bib19 article-title: Composition and dynamics of the activated sludge microbiome during seasonal nitrification failure publication-title: Sci. Rep. – volume: 44 start-page: 3523 year: 2022 end-page: 3542 ident: bib28 article-title: Image segmentation using deep learning: a survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 821 year: 2022 ident: bib32 article-title: Analysis and prediction of water quality using deep learning and auto deep learning techniques publication-title: Sci. Total Environ. – year: 2015 ident: bib15 article-title: Fast R-CNN – volume: 77 start-page: 2415 year: 2018 end-page: 2425 ident: bib29 article-title: New insights in morphological analysis for managing activated sludge systems publication-title: Water Sci. Technol. – start-page: 1 year: 2018 end-page: 6 ident: bib1 article-title: Understanding of a convolutional neural network publication-title: Proceedings of 2017 International Conference on Engineering and Technology – volume: 38 start-page: 2571 year: 2004 end-page: 2578 ident: bib36 article-title: Dynamics of nematodes in a high organic loading rotating biological contactors publication-title: Water Res. – volume: 133 start-page: 169 year: 2020 end-page: 182 ident: bib46 article-title: Application of artificial intelligence to wastewater treatment: a bibliometric analysis and systematic review of technology, economy, management, and wastewater reuse publication-title: Process Saf. Environ. Protect. – volume: 164 start-page: 16 year: 2010 end-page: 22 ident: bib20 article-title: Seasonal variability of biomass density and activated sludge settleability in full-scale wastewater treatment systems publication-title: Chem. Eng. J. – volume: 21 start-page: 265 year: 2019 end-page: 277 ident: bib14 article-title: Physicochemical properties of the sugar industry and ethanol distillery wastewater and their impact on the environment publication-title: Sugar Tech – year: 2019 ident: bib35 article-title: Tackling climate change with machine learning publication-title: ArXiv – volume: 40 start-page: 1975 year: 2019 end-page: 1986 ident: bib2 article-title: Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging publication-title: Eur. Heart J. – volume: 28 start-page: 67 year: 1994 end-page: 75 ident: bib25 article-title: A sludge biotic index (SBI) for the evaluation of the biological performance of activated sludge plants based on the microfauna analysis publication-title: Water Res. – volume: 10 start-page: 1711 year: 2021 ident: bib43 article-title: A real-time detection algorithm for kiwifruit defects based on YOLOv5 publication-title: Electronics – volume: 30 start-page: 3212 year: 2019 end-page: 3232 ident: bib45 article-title: Object detection with deep learning: a review publication-title: IEEE Transact. Neural Networks Learn. Syst. – volume: 802 start-page: 14 year: 2013 end-page: 28 ident: bib27 article-title: Activated sludge characterization through microscopy: a review on quantitative image analysis and chemometric techniques publication-title: Anal. Chim. Acta – year: 2017 ident: bib31 article-title: The effectiveness of data augmentation in image classification using deep learning – volume: 5 start-page: 28 year: 2015 end-page: 34 ident: bib22 article-title: On-line optical monitoring of activated sludge floc morphology publication-title: J. Water Proc. Eng. – start-page: 2020 year: 2020 ident: bib21 article-title: Comparison of faster-RCNN, YOLO, and SSD for real-time vehicle type recognition publication-title: IEEE International Conference on Consumer Electronics - Asia – volume: 832 year: 2022 ident: bib24 article-title: Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants publication-title: Sci. Total Environ. – year: 2010 ident: bib10 article-title: ImageNet: a large-scale hierarchical image database – volume: 29 start-page: 1703 year: 1995 end-page: 1710 ident: bib3 article-title: Influence of substrate loading intensity on floc size in activated sludge process publication-title: Water Res. – start-page: 257 year: 1998 end-page: 300 ident: bib23 article-title: Practical methods for the examination and characterization of activated sludge publication-title: The Microbiology of Activated Sludge – volume: 10 year: 2022 ident: bib44 article-title: Application of machine learning techniques to model a full-scale wastewater treatment plant with biological nutrient removal publication-title: J. Environ. Chem. Eng. – volume: 223 start-page: 694 year: 2019 end-page: 703 ident: bib7 article-title: Assessing activated sludge morphology and oxygen transfer performance using image analysis publication-title: Chemosphere – start-page: 278 year: 2018 end-page: 282 ident: bib8 article-title: Convolutional neural network (CNN) for image detection and recognition publication-title: ICSCCC 2018 - 1st International Conference on Secure Cyber Computing and Communications – volume: 167 start-page: 55 year: 2004 end-page: 63 ident: bib38 article-title: Developments in wastewater treatment methods publication-title: Desalination – volume: 9 start-page: 46 year: 2020 end-page: 64 ident: bib11 article-title: Comparative analysis on YOLO object detection with OpenCV publication-title: International Journal of Research in Industrial Engineering – volume: 41 start-page: 1814 year: 2007 end-page: 1822 ident: bib37 article-title: Density effects on activated sludge zone settling velocities publication-title: Water Res. – year: 2000 ident: bib13 article-title: Proces Control of Activated Sludge Plants by Microscopic Investigation – year: 2022 ident: bib41 article-title: The Global Risks Report 2022 – start-page: 6 year: 2021 end-page: 11 ident: bib47 article-title: Safety helmet detection based on YOLOv5 publication-title: Proceedings of 2021 IEEE International Conference on Power Electronics, Computer Applications – ident: bib34 article-title: Give your software the power to see objects in images and video – volume: 14 start-page: 158 year: 2004 end-page: 170 ident: bib9 article-title: A simple and effective histogram equalization approach to image enhancement publication-title: Digit. Signal Process. – volume: 999 start-page: 657 year: 2020 end-page: 668 ident: bib4 article-title: Deep learning techniques—R-CNN to mask R-CNN: a survey publication-title: Adv. Intell. Syst. Comput. – year: 2016 ident: bib33 article-title: You Only Look once: Unified, Real-Time Object Detection – volume: 28 start-page: 1471 year: 2021 end-page: 1496 ident: bib12 article-title: Histogram equalization variants as optimization problems: a review publication-title: Arch. Comput. Methods Eng. – year: 2019 ident: bib42 article-title: Detectron2 model zoo – year: 2010 ident: bib26 article-title: Protozoa in wastewater treatment processes: a minireview – year: 2021 ident: bib18 article-title: ultralytics/yolov5: v4.0 - nn.SiLU( ) activations, Weights & Biases logging publication-title: PyTorch Hub integration – volume: 45 start-page: 68 year: 1999 end-page: 75 ident: bib39 article-title: Image enhancement based on equal area dualistic sub-image histogram equalization method publication-title: IEEE Trans. Consum. Electron. – volume: 832 year: 2022 ident: 10.1016/j.jclepro.2023.137913_bib24 article-title: Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2022.154930 – ident: 10.1016/j.jclepro.2023.137913_bib5 – volume: 123 start-page: 578 year: 2017 ident: 10.1016/j.jclepro.2023.137913_bib6 article-title: The influence of protruding filamentous bacteria on floc stability and solid-liquid separation in the activated sludge process publication-title: Water Res. doi: 10.1016/j.watres.2017.06.063 – ident: 10.1016/j.jclepro.2023.137913_bib10 – volume: 38 start-page: 2571 year: 2004 ident: 10.1016/j.jclepro.2023.137913_bib36 article-title: Dynamics of nematodes in a high organic loading rotating biological contactors publication-title: Water Res. doi: 10.1016/j.watres.2004.03.007 – ident: 10.1016/j.jclepro.2023.137913_bib42 – volume: 43 start-page: 66 year: 2017 ident: 10.1016/j.jclepro.2023.137913_bib16 article-title: Use of DAIME for characterisation of activated sludge flocs publication-title: Arch. Environ. Protect. doi: 10.1515/aep-2017-0042 – volume: 28 start-page: 67 year: 1994 ident: 10.1016/j.jclepro.2023.137913_bib25 article-title: A sludge biotic index (SBI) for the evaluation of the biological performance of activated sludge plants based on the microfauna analysis publication-title: Water Res. doi: 10.1016/0043-1354(94)90120-1 – volume: 10 year: 2022 ident: 10.1016/j.jclepro.2023.137913_bib44 article-title: Application of machine learning techniques to model a full-scale wastewater treatment plant with biological nutrient removal publication-title: J. Environ. Chem. Eng. doi: 10.1016/j.jece.2022.107430 – start-page: 257 year: 1998 ident: 10.1016/j.jclepro.2023.137913_bib23 article-title: Practical methods for the examination and characterization of activated sludge publication-title: The Microbiology of Activated Sludge doi: 10.1007/978-94-011-3951-9_10 – year: 2022 ident: 10.1016/j.jclepro.2023.137913_bib41 – start-page: 1 year: 2018 ident: 10.1016/j.jclepro.2023.137913_bib1 article-title: Understanding of a convolutional neural network – volume: 223 start-page: 694 year: 2019 ident: 10.1016/j.jclepro.2023.137913_bib7 article-title: Assessing activated sludge morphology and oxygen transfer performance using image analysis publication-title: Chemosphere doi: 10.1016/j.chemosphere.2019.02.088 – volume: 21 start-page: 265 year: 2019 ident: 10.1016/j.jclepro.2023.137913_bib14 article-title: Physicochemical properties of the sugar industry and ethanol distillery wastewater and their impact on the environment publication-title: Sugar Tech doi: 10.1007/s12355-018-0633-z – volume: 802 start-page: 14 year: 2013 ident: 10.1016/j.jclepro.2023.137913_bib27 article-title: Activated sludge characterization through microscopy: a review on quantitative image analysis and chemometric techniques publication-title: Anal. Chim. Acta doi: 10.1016/j.aca.2013.09.016 – ident: 10.1016/j.jclepro.2023.137913_bib31 – year: 2021 ident: 10.1016/j.jclepro.2023.137913_bib18 article-title: ultralytics/yolov5: v4.0 - nn.SiLU( ) activations, Weights & Biases logging publication-title: PyTorch Hub integration – volume: 167 start-page: 55 year: 2004 ident: 10.1016/j.jclepro.2023.137913_bib38 article-title: Developments in wastewater treatment methods publication-title: Desalination doi: 10.1016/j.desal.2004.06.113 – volume: 44 start-page: 3523 year: 2022 ident: 10.1016/j.jclepro.2023.137913_bib28 article-title: Image segmentation using deep learning: a survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 45 start-page: 68 year: 1999 ident: 10.1016/j.jclepro.2023.137913_bib39 article-title: Image enhancement based on equal area dualistic sub-image histogram equalization method publication-title: IEEE Trans. Consum. Electron. doi: 10.1109/30.754419 – volume: 14 start-page: 158 year: 2004 ident: 10.1016/j.jclepro.2023.137913_bib9 article-title: A simple and effective histogram equalization approach to image enhancement publication-title: Digit. Signal Process. doi: 10.1016/j.dsp.2003.07.002 – volume: 40 start-page: 1975 year: 2019 ident: 10.1016/j.jclepro.2023.137913_bib2 article-title: Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging publication-title: Eur. Heart J. doi: 10.1093/eurheartj/ehy404 – volume: 28 start-page: 1471 year: 2021 ident: 10.1016/j.jclepro.2023.137913_bib12 article-title: Histogram equalization variants as optimization problems: a review publication-title: Arch. Comput. Methods Eng. doi: 10.1007/s11831-020-09425-1 – volume: 14 start-page: 1275 issue: 2022 year: 2022 ident: 10.1016/j.jclepro.2023.137913_bib30 article-title: Deep learning-based algal detection model development considering field application publication-title: Water doi: 10.3390/w14081275 – year: 2016 ident: 10.1016/j.jclepro.2023.137913_bib33 – volume: 133 start-page: 169 year: 2020 ident: 10.1016/j.jclepro.2023.137913_bib46 article-title: Application of artificial intelligence to wastewater treatment: a bibliometric analysis and systematic review of technology, economy, management, and wastewater reuse publication-title: Process Saf. Environ. Protect. doi: 10.1016/j.psep.2019.11.014 – volume: 41 start-page: 1814 year: 2007 ident: 10.1016/j.jclepro.2023.137913_bib37 article-title: Density effects on activated sludge zone settling velocities publication-title: Water Res. doi: 10.1016/j.watres.2007.01.011 – volume: 164 start-page: 16 year: 2010 ident: 10.1016/j.jclepro.2023.137913_bib20 article-title: Seasonal variability of biomass density and activated sludge settleability in full-scale wastewater treatment systems publication-title: Chem. Eng. J. doi: 10.1016/j.cej.2010.07.061 – year: 2019 ident: 10.1016/j.jclepro.2023.137913_bib35 article-title: Tackling climate change with machine learning publication-title: ArXiv – year: 2015 ident: 10.1016/j.jclepro.2023.137913_bib15 – volume: 42 start-page: 2300 year: 2008 ident: 10.1016/j.jclepro.2023.137913_bib40 article-title: Microbial community structure in activated sludge floc analysed by fluorescence in situ hybridization and its relation to floc stability publication-title: Water Res. doi: 10.1016/j.watres.2007.12.013 – volume: 9 start-page: 1 issue: 1 9 year: 2019 ident: 10.1016/j.jclepro.2023.137913_bib19 article-title: Composition and dynamics of the activated sludge microbiome during seasonal nitrification failure publication-title: Sci. Rep. – ident: 10.1016/j.jclepro.2023.137913_bib34 – volume: 10 start-page: 1711 issue: 2021 year: 2021 ident: 10.1016/j.jclepro.2023.137913_bib43 article-title: A real-time detection algorithm for kiwifruit defects based on YOLOv5 publication-title: Electronics doi: 10.3390/electronics10141711 – volume: 999 start-page: 657 year: 2020 ident: 10.1016/j.jclepro.2023.137913_bib4 article-title: Deep learning techniques—R-CNN to mask R-CNN: a survey publication-title: Adv. Intell. Syst. Comput. doi: 10.1007/978-981-13-9042-5_56 – start-page: 2020 year: 2020 ident: 10.1016/j.jclepro.2023.137913_bib21 article-title: Comparison of faster-RCNN, YOLO, and SSD for real-time vehicle type recognition – ident: 10.1016/j.jclepro.2023.137913_bib26 – volume: 30 start-page: 3212 year: 2019 ident: 10.1016/j.jclepro.2023.137913_bib45 article-title: Object detection with deep learning: a review publication-title: IEEE Transact. Neural Networks Learn. Syst. doi: 10.1109/TNNLS.2018.2876865 – volume: 29 start-page: 1703 year: 1995 ident: 10.1016/j.jclepro.2023.137913_bib3 article-title: Influence of substrate loading intensity on floc size in activated sludge process publication-title: Water Res. doi: 10.1016/0043-1354(94)00326-3 – volume: 821 year: 2022 ident: 10.1016/j.jclepro.2023.137913_bib32 article-title: Analysis and prediction of water quality using deep learning and auto deep learning techniques publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2022.153311 – start-page: 278 year: 2018 ident: 10.1016/j.jclepro.2023.137913_bib8 article-title: Convolutional neural network (CNN) for image detection and recognition publication-title: ICSCCC 2018 - 1st International Conference on Secure Cyber Computing and Communications – volume: 77 start-page: 2415 year: 2018 ident: 10.1016/j.jclepro.2023.137913_bib29 article-title: New insights in morphological analysis for managing activated sludge systems publication-title: Water Sci. Technol. doi: 10.2166/wst.2018.189 – year: 2000 ident: 10.1016/j.jclepro.2023.137913_bib13 – volume: 5 start-page: 28 year: 2015 ident: 10.1016/j.jclepro.2023.137913_bib22 article-title: On-line optical monitoring of activated sludge floc morphology publication-title: J. Water Proc. Eng. doi: 10.1016/j.jwpe.2014.12.009 – start-page: 6 year: 2021 ident: 10.1016/j.jclepro.2023.137913_bib47 article-title: Safety helmet detection based on YOLOv5 – volume: 9 start-page: 46 year: 2020 ident: 10.1016/j.jclepro.2023.137913_bib11 article-title: Comparative analysis on YOLO object detection with OpenCV publication-title: International Journal of Research in Industrial Engineering |
| SSID | ssj0017074 |
| Score | 2.531208 |
| Snippet | The activated sludge (AS) process is the most common type of secondary wastewater treatment, applied worldwide. Due to the complexity of microbial communities,... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 137913 |
| SubjectTerms | Activated sludge algorithms Computer vision Deep learning pollution Protozoa Secondary treatment Wastewater wastewater treatment Water quality water reuse |
| Title | Analyzing the secondary wastewater-treatment process using Faster R-CNN and YOLOv5 object detection algorithms |
| URI | https://dx.doi.org/10.1016/j.jclepro.2023.137913 https://www.proquest.com/docview/2922029733 |
| Volume | 416 |
| WOSCitedRecordID | wos001036439000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-1786 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017074 issn: 0959-6526 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELZglwMcEE-xvGQkxKVKydv2cbVqRVdVi6BI5WTZjkNbrZLQpsuKX884dtIKinY5cIkiK3aSmS-T8TwRest8X0e5FJ6S0hTVJrEnCEs9lgXUqMs6EbRpNkEmEzqfs4_OqrRp2gmQoqBXV6z6r6yGMWC2SZ39B3Z3i8IAnAPT4Qhsh-ONGN-UGfnZZkFtzIY3M6FxP8TGGMqAjt4uuryyeQK9bWMyGJpL1r1P3tlk0ngVvk7H08ukV0pjrellutaus_jFt3K9rBeu1Pmfyi08kyhgqcoWlN1z9o8KaWO6p3m-7CKDPy_Ewg4bIdMFBS2ztY0KOAfBLTt_SZtSMsrKfatFGHVhWfvmxzSx2fKtJAblsFf1g4iwIPIOyndralj1V_Aa8AZ9s7SbsPuhtU78yZQPv4zHfDaYz95V3z3Tasy45F3fldvoOCQJA1F4fDoazM875xPxbfHu9hF3iV_vD975byrNbz_3RmOZPUD3HTfwqYXIQ3RLF4_Qvb0ClI9R0YEFA1hwBxZ8CCzYgQU3YMEWLLgBCwawYAsWbMGCO7DgHVieoNlwMDv74LkOHJ6K4rD2ssxPZEDzOBUqTmPY7gopdB6IIIppplgQE-lLnWidZ6B3-3mYKkkFY0QRowg-RUdFWehnCEeZMg5gQQVVsfEuU6p8SmSscyIki05Q3NKQK1ed3jRJueBtGOKKO9JzQ3puSX-C-t20ypZnuW4CbRnEnY5pdUcOELtu6puWoRxksHGswZdUbjc8ZGHYNIGLnt_gmhfo7u6LeImO6vVWv0J31GW93KxfOzD-ArFurRQ |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Analyzing+the+secondary+wastewater-treatment+process+using+Faster+R-CNN+and+YOLOv5+object+detection+algorithms&rft.jtitle=Journal+of+cleaner+production&rft.au=Inbar%2C+Offir&rft.au=Shahar%2C+Moni&rft.au=Gidron%2C+Jacob&rft.au=Cohen%2C+Ido&rft.date=2023-09-01&rft.issn=0959-6526&rft.volume=416+p.137913-&rft_id=info:doi/10.1016%2Fj.jclepro.2023.137913&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0959-6526&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0959-6526&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0959-6526&client=summon |