Centre de documentation
scientifique

Adversarial defenses for object detectors based on Gabor convolutional layers / Abdollah Amirkhani in The Visual Computer, vol 38 n° 6 (June 2022)  

Public [article]  inThe Visual Computer > vol 38 n° 6 (June 2022) . - pp 1929 - 1944 Titre : Adversarial defenses for object detectors based on Gabor convolutional layers Type de document : Article/Communication Auteurs : Abdollah Amirkhani, Auteur ; Mohammad Karimi, Auteur Année de publication : 2022 Article en page(s) : pp 1929 - 1944 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] détection d'objet [Termes IGN] filtre de Gabor [Termes IGN] reconnaissance de formes [Termes IGN] réseau antagoniste génératif Résumé : (auteur) Despite their many advantages and positive features, the deep neural networks are extremely vulnerable against adversarial attacks. This drawback has substantially reduced the adversarial accuracy of the visual object detectors. To make these object detectors robust to adversarial attacks, a new Gabor filter-based method has been proposed in this paper. This method has then been applied on the YOLOv3 with different backbones, the SSD with different input sizes and on the FRCNN; and thus, six robust object detector models have been presented. In order to evaluate the efficacy of the models, they have been subjected to adversarial training via three types of targeted attacks (TOG-fabrication, TOG-vanishing, and TOG-mislabeling) and three types of untargeted random attacks (DAG, RAP, and UEA). The best average accuracy (49.6%) was achieved by the YOLOv3-d model, and for the PASCAL VOC dataset. This is far superior to the best performance and accuracy and obtained in previous works (25.4%). Empirical results show that, while the presented approach improves the adversarial accuracy of the object detector models, it does not affect the performance of these models on clean data. Numéro de notice : A2022-382 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-021-02256-6 Date de publication en ligne : 24/07/2021 En ligne : https://doi.org/10.1007/s00371-021-02256-6 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100651 [article]

Agricultural land partitioning model based on irrigation efficiency using a multi‐objective artificial bee colony algorithm / Mehrdad Bijandi in Transactions in GIS, Vol 25 n° 1 (February 2021)  

Public [article]  inTransactions in GIS > Vol 25 n° 1 (February 2021) . - pp 551 - 574 Titre : Agricultural land partitioning model based on irrigation efficiency using a multi‐objective artificial bee colony algorithm Type de document : Article/Communication Auteurs : Mehrdad Bijandi, Auteur ; Mohammad Karimi, Auteur ; Bahman Farhadi Bansouleh, Auteur ; Wim van der Knaap, Auteur Année de publication : 2021 Article en page(s) : pp 551 - 574 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] données topographiques [Termes IGN] irrigation [Termes IGN] optimisation par colonie de fourmis [Termes IGN] parcelle agricole [Termes IGN] planification [Termes IGN] remembrement agricole [Termes IGN] surface cultivée [Termes IGN] utilisation du sol Résumé : (Auteur) In the process of agricultural land consolidation, the land parcels are optimally redesigned and rearranged in such a way that the dimensions of the resulting parcels are proportional to agricultural criteria such as irrigation discharge, soil texture, and cropping pattern. Besides these criteria, spatial factors like slope, road accessibility, volume of earthwork, and geometrical factors such as size and shape of parcels are also included in the design process of agricultural land partitioning. In this study, a land partitioning model was proposed using a multi‐objective artificial bee colony algorithm (MOABC‐LP) taking into consideration the mentioned factors. Initially, a feasible dimension range of parcels in a block was calculated based on irrigation efficiency. Two partitioning layouts were defined according to the topography and geometry of blocks. The proposed method was applied to a real study area and the results suggest that the land partitioning plan obtained by the MOABC‐LP model, in comparison with a designer's plan, not only makes the shape and size of parcels more compatible with the topographical and agricultural conditions of each block, but also reduces their cut‐and‐fill ratio. Numéro de notice : A2021-210 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12702 Date de publication en ligne : 27/10/2020 En ligne : https://doi.org/10.1111/tgis.12702 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97159 [article]

A novel approach to site selection: collaborative multi-criteria decision making through geo-social network (case study: public parking) / Zeinab Neisani Samani in ISPRS International journal of geo-information, vol 7 n° 3 (March 2018)  

Public [article]  inISPRS International journal of geo-information > vol 7 n° 3 (March 2018) Titre : A novel approach to site selection: collaborative multi-criteria decision making through geo-social network (case study: public parking) Type de document : Article/Communication Auteurs : Zeinab Neisani Samani, Auteur ; Mohammad Karimi, Auteur ; Ali Asghar Alesheikh, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] aide à la décision [Termes IGN] analyse multicritère [Termes IGN] parking [Termes IGN] processus de hiérarchisation analytique [Termes IGN] réseau social [Termes IGN] Téhéran Résumé : (Auteur) There are many potential factors that are involved in the decision making process of site selection, which makes it a challenging issue. This paper addresses the collaborative decision making concept through a geo-social network to predict site selection for public parking in Tehran, Iran. The presented approach utilized the analytic hierarchy process (AHP) as a multi-criteria decision method (MCDM) for weighting the criteria, which was completed in two stages; once by 50 experts, and then by three different levels of users, including 50 experts, 25 urban managers, and 150 pubic citizens, with respect to the case study area. The fuzzy majority method aggregates the archived results of AHP to determine the preferred locations that are suitable for public parking. The proposed method was implemented using a telegram bot platform. Two main advantages of the collaborative decision making scenario for public urban site selection are the fair distribution of the selected locations and the high satisfaction of users, which increased from 65% to 85%. This study presents an application for site selection based on multi-criteria decision making in a geo-social network context. Numéro de notice : A2018-098 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi7030082 En ligne : https://doi.org/10.3390/ijgi7030082 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89513 [article]