{"id":4182,"date":"2024-04-28T18:21:04","date_gmt":"2024-04-28T23:21:04","guid":{"rendered":"https:\/\/cirics.uqo.ca\/mohand-said-allili\/"},"modified":"2025-02-07T10:04:09","modified_gmt":"2025-02-07T15:04:09","slug":"mohand-said-allili","status":"publish","type":"page","link":"https:\/\/cirics.uqo.ca\/en\/mohand-said-allili\/","title":{"rendered":"Mohand Said Allili"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"4182\" class=\"elementor elementor-4182 elementor-2523\">\n\t\t\t\t<div class=\"elementor-element elementor-element-e09216a e-flex e-con-boxed e-con e-parent\" data-id=\"e09216a\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-9386cfe elementor-hidden-desktop elementor-hidden-tablet elementor-hidden-mobile e-flex e-con-boxed e-con e-parent\" data-id=\"9386cfe\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-ea9c07d elementor-widget elementor-widget-heading\" data-id=\"ea9c07d\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Welcome<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-70e53c3 elementor-widget elementor-widget-text-editor\" data-id=\"70e53c3\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>If needed, this section can contain some or all of the following:<\/p>\n<ul>\n<li>A large, engaging image of the university, department, or an abstract representation of the academic field can set a professional and inspiring tone.<\/li>\n<li>A brief welcome message or introduction that explains what visitors will find on the page. This could be a short paragraph detailing the purpose of the page, such as highlighting the academic and research achievements of the faculty.<\/li>\n<li>Key facts, achievements or statistics about the professor or department. For instance, number of published papers, years of experience, key projects, or awards won.<\/li>\n<li>Interactive timeline that highlights major milestones, such as significant publications, awards, and other achievements.<\/li>\n<li>A short video where the professor introduces themselves and talk about their work and interests providing a personal touch, and making the page more engaging and approachable.<\/li>\n<\/ul>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-9b8f585 e-flex e-con-boxed e-con e-parent\" data-id=\"9b8f585\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-99badd5 e-con-full my-profs-page-image-card e-flex e-con e-child\" data-id=\"99badd5\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-d8d58ce eael-team-align-centered elementor-widget elementor-widget-eael-team-member\" data-id=\"d8d58ce\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"eael-team-member.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\n\n\t<div id=\"eael-team-member-d8d58ce\" class=\"eael-team-item eael-team-members-simple team-avatar-rounded\">\n\t\t<div class=\"eael-team-item-inner\">\n\t\t\t<div class=\"eael-team-image\">\n\t\t\t\t<figure>\n\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" src=\"https:\/\/cirics.uqo.ca\/wp-content\/uploads\/2024\/04\/Mohand_Said_Allili-300x300-1.webp\" alt=\"\">\n\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\n\t\t\t\t\n\t\t\t<\/div>\n\n\t\t\t<div class=\"eael-team-content\">\n\t\t\t\t<h2 class=\"eael-team-member-name\">Mohand Said Allili<\/h2><h3 class=\"eael-team-member-position\"><span>Professor<\/span><br> Universit\u00e9 du Qu\u00e9bec en Outaouais (UQO)<br> Computer Science and Engineering Department<\/h3>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<ul class=\"eael-team-member-social-profiles\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<li class=\"eael-team-member-social-link\">\n\t\t\t\t\t\t\t\t\t\t<a href=\"https:\/\/uqo.ca\/profil\/allimo01\" target=\"_blank\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-university\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M496 128v16a8 8 0 0 1-8 8h-24v12c0 6.627-5.373 12-12 12H60c-6.627 0-12-5.373-12-12v-12H24a8 8 0 0 1-8-8v-16a8 8 0 0 1 4.941-7.392l232-88a7.996 7.996 0 0 1 6.118 0l232 88A8 8 0 0 1 496 128zm-24 304H40c-13.255 0-24 10.745-24 24v16a8 8 0 0 0 8 8h464a8 8 0 0 0 8-8v-16c0-13.255-10.745-24-24-24zM96 192v192H60c-6.627 0-12 5.373-12 12v20h416v-20c0-6.627-5.373-12-12-12h-36V192h-64v192h-64V192h-64v192h-64V192H96z\"><\/path><\/svg>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<li class=\"eael-team-member-social-link\">\n\t\t\t\t\t\t\t\t\t\t<a href=\"http:\/\/w3.uqo.ca\/allimo01\/\" target=\"_blank\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fab-wordpress\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M61.7 169.4l101.5 278C92.2 413 43.3 340.2 43.3 256c0-30.9 6.6-60.1 18.4-86.6zm337.9 75.9c0-26.3-9.4-44.5-17.5-58.7-10.8-17.5-20.9-32.4-20.9-49.9 0-19.6 14.8-37.8 35.7-37.8.9 0 1.8.1 2.8.2-37.9-34.7-88.3-55.9-143.7-55.9-74.3 0-139.7 38.1-177.8 95.9 5 .2 9.7.3 13.7.3 22.2 0 56.7-2.7 56.7-2.7 11.5-.7 12.8 16.2 1.4 17.5 0 0-11.5 1.3-24.3 2l77.5 230.4L249.8 247l-33.1-90.8c-11.5-.7-22.3-2-22.3-2-11.5-.7-10.1-18.2 1.3-17.5 0 0 35.1 2.7 56 2.7 22.2 0 56.7-2.7 56.7-2.7 11.5-.7 12.8 16.2 1.4 17.5 0 0-11.5 1.3-24.3 2l76.9 228.7 21.2-70.9c9-29.4 16-50.5 16-68.7zm-139.9 29.3l-63.8 185.5c19.1 5.6 39.2 8.7 60.1 8.7 24.8 0 48.5-4.3 70.6-12.1-.6-.9-1.1-1.9-1.5-2.9l-65.4-179.2zm183-120.7c.9 6.8 1.4 14 1.4 21.9 0 21.6-4 45.8-16.2 76.2l-65 187.9C426.2 403 468.7 334.5 468.7 256c0-37-9.4-71.8-26-102.1zM504 256c0 136.8-111.3 248-248 248C119.2 504 8 392.7 8 256 8 119.2 119.2 8 256 8c136.7 0 248 111.2 248 248zm-11.4 0c0-130.5-106.2-236.6-236.6-236.6C125.5 19.4 19.4 125.5 19.4 256S125.6 492.6 256 492.6c130.5 0 236.6-106.1 236.6-236.6z\"><\/path><\/svg>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/ul>\n\t\t\t\t\t\t\t\t\t\t<p class=\"eael-team-text\">Mohand Said Allili is a full professor in the Department of Computer Science and Engineering at the Universit\u00e9 du Qu\u00e9bec en Outaouais, where he heads the Imaging, Vision and Artificial Intelligence Research Laboratory (LARIVIA). Its research activities revolve around computer vision, machine learning and multimedia data processing, with applications in the semantic analysis of medical and aerial images, and cybersecurity.  <\/p>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-aaa41d5 e-con-full my-profs-page-publ-card e-flex e-con e-child\" data-id=\"aaa41d5\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-a474f56 elementor-widget elementor-widget-heading\" data-id=\"a474f56\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Productions included in the research:<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ce5ef54 elementor-widget elementor-widget-text-editor\" data-id=\"ce5ef54\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: left;\"><strong>AUT<\/strong> (Other), BRE (Patent), <strong>CAC<\/strong> (Refereed publications in conference proceedings), <strong>CNA<\/strong> (Non-refereed paper), <strong>COC<\/strong> (Contribution to a collective work), <strong>COF<\/strong> (Refereed paper), <strong>CRE<\/strong>, <strong>GRO<\/strong>, <strong>LIV<\/strong> (Book), <strong>RAC<\/strong> (Refereed journal), <strong>RAP<\/strong> (Research report), <strong>RSC<\/strong> (Non-refereed journal).<\/p>\n<p style=\"text-align: center;\"><span style=\"text-shadow: 1px 1px 2px gray;\">Year: 1975 to 2024<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-107306a elementor-align-center my-prof-publ-but elementor-widget elementor-widget-button\" data-id=\"107306a\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/cirics.uqo.ca\/publications\/?tsr=&#038;auth=141\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-icon\">\n\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-book-open\" viewBox=\"0 0 576 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M542.22 32.05c-54.8 3.11-163.72 14.43-230.96 55.59-4.64 2.84-7.27 7.89-7.27 13.17v363.87c0 11.55 12.63 18.85 23.28 13.49 69.18-34.82 169.23-44.32 218.7-46.92 16.89-.89 30.02-14.43 30.02-30.66V62.75c.01-17.71-15.35-31.74-33.77-30.7zM264.73 87.64C197.5 46.48 88.58 35.17 33.78 32.05 15.36 31.01 0 45.04 0 62.75V400.6c0 16.24 13.13 29.78 30.02 30.66 49.49 2.6 149.59 12.11 218.77 46.95 10.62 5.35 23.21-1.94 23.21-13.46V100.63c0-5.29-2.62-10.14-7.27-12.99z\"><\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">All publications<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-eb6a7a7 elementor-widget elementor-widget-heading\" data-id=\"eb6a7a7\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Selected publications<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-29ef351 elementor-widget elementor-widget-shortcode\" data-id=\"29ef351\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"shortcode.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<div class=\"elementor-shortcode\"><div class=\"teachpress_pub_list\"><form name=\"tppublistform\" method=\"get\"><a name=\"tppubs\" id=\"tppubs\"><\/a><\/form><table class=\"teachpress_publication_list\"><tr>\r\n                    <td>\r\n                        <h3 class=\"tp_h3\" id=\"tp_h3_2027\">2027<\/h3>\r\n                    <\/td>\r\n                <\/tr><tr class=\"tp_publication tp_publication_article\"><td class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Allaoui, M. L.;  Allili, M. S.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('646','tp_abstract')\" style=\"cursor:pointer;\">LG-TargetSeg: Deep semantic fusion via language-conditioned selective scanning for targeted medical image segmentation<\/a> <span class=\"tp_pub_type tp_  article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Information Fusion, <\/span><span class=\"tp_pub_additional_volume\">vol. 139, <\/span><span class=\"tp_pub_additional_year\">2027<\/span>, <span class=\"tp_pub_additional_issn\">ISSN: 15662535 (ISSN)<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_abstract_link\"><a id=\"tp_abstract_sh_646\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('646','tp_abstract')\" title=\"Show abstract\" style=\"cursor:pointer;\">Abstract<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_646\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('646','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span>  |  <span class=\"tp_pub_links_label\">Links: <\/span><a class=\"tp_pub_link\" href=\"https:\/\/www.scopus.com\/pages\/publications\/105051242411?origin=resultslist\" title=\"https:\/\/www.scopus.com\/pages\/publications\/105051242411?origin=resultslist\" target=\"_blank\"><i class=\"fas fa-globe\"><\/i><\/a><a class=\"tp_pub_link\" href=\"https:\/\/dx.doi.org\/10.1016\/j.inffus.2026.104797\" title=\"Follow DOI:10.1016\/j.inffus.2026.104797\" target=\"_blank\"><i class=\"ai ai-doi\"><\/i><\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_646\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{allaouiLGTargetSegDeepSemantic2027,<br \/>\r\ntitle = {LG-TargetSeg: Deep semantic fusion via language-conditioned selective scanning for targeted medical image segmentation},<br \/>\r\nauthor = {M. L. Allaoui and M. S. Allili},<br \/>\r\nurl = {https:\/\/www.scopus.com\/pages\/publications\/105051242411?origin=resultslist},<br \/>\r\ndoi = {10.1016\/j.inffus.2026.104797},<br \/>\r\nissn = {15662535 (ISSN)},<br \/>\r\nyear  = {2027},<br \/>\r\ndate = {2027-01-01},<br \/>\r\njournal = {Information Fusion},<br \/>\r\nvolume = {139},<br \/>\r\npublisher = {Elsevier B.V.},<br \/>\r\nabstract = {Clinical language defines the semantic intent of targeted medical image segmentation, yet most vision\u2013language methods incorporate it only at a shallow level or through training-time conditioning, leaving spatial reasoning largely language-blind. We propose LG-TargetSeg (Language-Guided Targeted Segmentation), a cross-modal framework that embeds clinical language directly into the selective scan of a Mamba-based encoder-decoder. Natural-language prompts, encoded by a frozen MedSigLIP foundation model, shape selective scanning throughout the encoder\u2013decoder and additionally adapt the bottleneck state transition, alongside gated modulation and cross-attention, enabling semantic guidance to continuously shape feature propagation toward the target anatomy. A Text-Driven Selective Scan 2D (TD-SS2D) module achieves prompt-aware multi-scale fusion with linear complexity in the number of spatial tokens. To improve robustness to boundary ambiguity and class imbalance, we introduce the Reinforced Gaussian Dice Loss (RGDL) with learnable weighting parameters. Evaluated under both task-specific and universal generalization settings, LG-TargetSeg achieves state-of-the-art performance. Moreover, its prompt-driven selectivity remains reliable under genuine multi-target competition: on abdominal CT images containing up to 16 annotated organs, changing only the text prompt on a frozen model produces organ masks with less than 1% pairwise overlap. Additional materials and code are available at: https:\/\/github.com\/MOHAMEDLamine77\/LG-TargetSeg . \u00a9 2026 Elsevier B.V.},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('646','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_abstract\" id=\"tp_abstract_646\" style=\"display:none;\"><div class=\"tp_abstract_entry\">Clinical language defines the semantic intent of targeted medical image segmentation, yet most vision\u2013language methods incorporate it only at a shallow level or through training-time conditioning, leaving spatial reasoning largely language-blind. We propose LG-TargetSeg (Language-Guided Targeted Segmentation), a cross-modal framework that embeds clinical language directly into the selective scan of a Mamba-based encoder-decoder. Natural-language prompts, encoded by a frozen MedSigLIP foundation model, shape selective scanning throughout the encoder\u2013decoder and additionally adapt the bottleneck state transition, alongside gated modulation and cross-attention, enabling semantic guidance to continuously shape feature propagation toward the target anatomy. A Text-Driven Selective Scan 2D (TD-SS2D) module achieves prompt-aware multi-scale fusion with linear complexity in the number of spatial tokens. To improve robustness to boundary ambiguity and class imbalance, we introduce the Reinforced Gaussian Dice Loss (RGDL) with learnable weighting parameters. Evaluated under both task-specific and universal generalization settings, LG-TargetSeg achieves state-of-the-art performance. Moreover, its prompt-driven selectivity remains reliable under genuine multi-target competition: on abdominal CT images containing up to 16 annotated organs, changing only the text prompt on a frozen model produces organ masks with less than 1% pairwise overlap. Additional materials and code are available at: https:\/\/github.com\/MOHAMEDLamine77\/LG-TargetSeg . \u00a9 2026 Elsevier B.V.<\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('646','tp_abstract')\">Close<\/a><\/p><\/div><\/td><\/tr><tr>\r\n                    <td>\r\n                        <h3 class=\"tp_h3\" id=\"tp_h3_2026\">2026<\/h3>\r\n                    <\/td>\r\n                <\/tr><tr class=\"tp_publication tp_publication_article\"><td class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Abdollahzadeh, S.;  Allili, M. S.;  Boulmerka, A.;  Lapointe, J. -F.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('546','tp_abstract')\" style=\"cursor:pointer;\">A Vision-Based Framework for Safe Landing Zone Mapping of UAVs in Dynamic Environments<\/a> <span class=\"tp_pub_type tp_  article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">IEEE Open Journal of the Computer Society, <\/span><span class=\"tp_pub_additional_volume\">vol. 7, <\/span><span class=\"tp_pub_additional_pages\">pp. 492\u2013503, <\/span><span class=\"tp_pub_additional_year\">2026<\/span>, <span class=\"tp_pub_additional_issn\">ISSN: 26441268 (ISSN)<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_abstract_link\"><a id=\"tp_abstract_sh_546\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('546','tp_abstract')\" title=\"Show abstract\" style=\"cursor:pointer;\">Abstract<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_546\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('546','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span>  |  <span class=\"tp_pub_links_label\">Links: <\/span><a class=\"tp_pub_link\" href=\"https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-105029942397&amp;doi=10.1109%2FOJCS.2026.3663268&amp;partnerID=40&amp;md5=b11484e035458c84b1d3f6780b92c91c\" title=\"https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-105029942397&amp;doi=10.1109%2FOJCS.2026.3663268&amp;partnerID=40&amp;md5=b11484e035458c84b1d3f6780b92c91c\" target=\"_blank\"><i class=\"fas fa-globe\"><\/i><\/a><a class=\"tp_pub_link\" href=\"https:\/\/dx.doi.org\/10.1109\/OJCS.2026.3663268\" title=\"Follow DOI:10.1109\/OJCS.2026.3663268\" target=\"_blank\"><i class=\"ai ai-doi\"><\/i><\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_546\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{abdollahzadeh_vision-based_2026,<br \/>\r\ntitle = {A Vision-Based Framework for Safe Landing Zone Mapping of UAVs in Dynamic Environments},<br \/>\r\nauthor = {S. Abdollahzadeh and M. S. Allili and A. Boulmerka and J. -F. Lapointe},<br \/>\r\nurl = {https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-105029942397&doi=10.1109%2FOJCS.2026.3663268&partnerID=40&md5=b11484e035458c84b1d3f6780b92c91c},<br \/>\r\ndoi = {10.1109\/OJCS.2026.3663268},<br \/>\r\nissn = {26441268 (ISSN)},<br \/>\r\nyear  = {2026},<br \/>\r\ndate = {2026-01-01},<br \/>\r\njournal = {IEEE Open Journal of the Computer Society},<br \/>\r\nvolume = {7},<br \/>\r\npages = {492\u2013503},<br \/>\r\nabstract = {Identification safe landing zones (SLZ) for Uncrewed Aerial Vehicles (UAVs) is important to ensure reliable and safe navigation, especially when they are operated in complex and safety-critical environments. However, this is a challenging task due to obstacles and UAV motion. This paper proposes a vision-based framework that maps SLZs in dynamic scenes by integrating several functionalities for analyzing visually static and dynamic aspects of a scene. Static analysis is achieved through context-aware segmentation which divides the image into thematic classes enabling to identify suitable landing surfaces (e.g., roads, grass). For dynamic content analysis, we combine object detection, tracking, and trajectory prediction to determine object occupancy and identify regions free of obstacles. Trajectory prediction is performed through a novel encoder\u2013decoder architecture taking past object positions to predict the most likely future locations. To ensure stable and robust trajectory prediction, we introduce an optimized homography computation using multi-scale image analysis and cumulative updates to compensate UAV motion. We tested our framework on different operational scenarios, including urban and natural scenes with moving objects like vehicles and pedestrians. Obtained results demonstrate its strong performance, and its significant potential for enabling autonomous and safe UAV navigation. \u00a9 2020 IEEE.},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('546','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_abstract\" id=\"tp_abstract_546\" style=\"display:none;\"><div class=\"tp_abstract_entry\">Identification safe landing zones (SLZ) for Uncrewed Aerial Vehicles (UAVs) is important to ensure reliable and safe navigation, especially when they are operated in complex and safety-critical environments. However, this is a challenging task due to obstacles and UAV motion. This paper proposes a vision-based framework that maps SLZs in dynamic scenes by integrating several functionalities for analyzing visually static and dynamic aspects of a scene. Static analysis is achieved through context-aware segmentation which divides the image into thematic classes enabling to identify suitable landing surfaces (e.g., roads, grass). For dynamic content analysis, we combine object detection, tracking, and trajectory prediction to determine object occupancy and identify regions free of obstacles. Trajectory prediction is performed through a novel encoder\u2013decoder architecture taking past object positions to predict the most likely future locations. To ensure stable and robust trajectory prediction, we introduce an optimized homography computation using multi-scale image analysis and cumulative updates to compensate UAV motion. We tested our framework on different operational scenarios, including urban and natural scenes with moving objects like vehicles and pedestrians. Obtained results demonstrate its strong performance, and its significant potential for enabling autonomous and safe UAV navigation. \u00a9 2020 IEEE.<\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('546','tp_abstract')\">Close<\/a><\/p><\/div><\/td><\/tr><tr class=\"tp_publication tp_publication_article\"><td class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Gapski, M. C. B.;  Kawai, V. A. S.;  Leticio, G. R.;  Valem, L. P.;  Pedronette, D. C. G.;  Allili, M. S.<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('654','tp_abstract')\" style=\"cursor:pointer;\">Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation<\/a> <span class=\"tp_pub_type tp_  article\">Journal Article<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_in\">In: <\/span><span class=\"tp_pub_additional_journal\">Journal of the Brazilian Computer Society, <\/span><span class=\"tp_pub_additional_volume\">vol. 32, <\/span><span class=\"tp_pub_additional_number\">no. 1, <\/span><span class=\"tp_pub_additional_pages\">pp. 1731\u20131754, <\/span><span class=\"tp_pub_additional_year\">2026<\/span>, <span class=\"tp_pub_additional_issn\">ISSN: 01046500 (ISSN)<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_abstract_link\"><a id=\"tp_abstract_sh_654\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('654','tp_abstract')\" title=\"Show abstract\" style=\"cursor:pointer;\">Abstract<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_654\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('654','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span>  |  <span class=\"tp_pub_links_label\">Links: <\/span><a class=\"tp_pub_link\" href=\"https:\/\/www.scopus.com\/pages\/publications\/105045179876?origin=resultslist\" title=\"https:\/\/www.scopus.com\/pages\/publications\/105045179876?origin=resultslist\" target=\"_blank\"><i class=\"fas fa-globe\"><\/i><\/a><a class=\"tp_pub_link\" href=\"https:\/\/dx.doi.org\/10.5753\/jbcs.2026.5880\" title=\"Follow DOI:10.5753\/jbcs.2026.5880\" target=\"_blank\"><i class=\"ai ai-doi\"><\/i><\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_654\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@article{gapskiGraphNeuralNetworks2026,<br \/>\r\ntitle = {Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation},<br \/>\r\nauthor = {M. C. B. Gapski and V. A. S. Kawai and G. R. Leticio and L. P. Valem and D. C. G. Pedronette and M. S. Allili},<br \/>\r\nurl = {https:\/\/www.scopus.com\/pages\/publications\/105045179876?origin=resultslist},<br \/>\r\ndoi = {10.5753\/jbcs.2026.5880},<br \/>\r\nissn = {01046500 (ISSN)},<br \/>\r\nyear  = {2026},<br \/>\r\ndate = {2026-01-01},<br \/>\r\njournal = {Journal of the Brazilian Computer Society},<br \/>\r\nvolume = {32},<br \/>\r\nnumber = {1},<br \/>\r\npages = {1731\u20131754},<br \/>\r\npublisher = {Brazilian Computing Society},<br \/>\r\nabstract = {Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy. \u00a9 2026, Brazilian Computing Society. All rights reserved.},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {article}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('654','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_abstract\" id=\"tp_abstract_654\" style=\"display:none;\"><div class=\"tp_abstract_entry\">Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy. \u00a9 2026, Brazilian Computing Society. All rights reserved.<\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('654','tp_abstract')\">Close<\/a><\/p><\/div><\/td><\/tr><\/table><\/div><\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-5558b72 elementor-hidden-desktop elementor-hidden-tablet elementor-hidden-mobile e-flex e-con-boxed e-con e-parent\" data-id=\"5558b72\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-92ea5b7 elementor-widget elementor-widget-heading\" data-id=\"92ea5b7\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Some Heading<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-de7d7a3 elementor-widget elementor-widget-text-editor\" data-id=\"de7d7a3\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>If needed, this section can contain some or all of the following:<\/p>\n<ul>\n<li>Recent news, updates, or upcoming events related to the professor or their department, such as guest lectures, seminars, and conferences.<\/li>\n<li>Social media feed.<\/li>\n<li>A quote from the professor about their philosophy on education and research or a testimonial from a peer or student adding a personal and inspirational element to the page, placing this information just above the share icons can give visitors current and relevant reasons to engage and share.<\/li>\n<li>Call to Action to attend or participate in some even.<\/li>\n<li>Contact Form<\/li>\n<li>Subscribe form<\/li>\n<\/ul>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-931098e e-flex e-con-boxed e-con e-parent\" data-id=\"931098e\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-ccca712 elementor-widget__width-auto eael-dual-header-content-align-center elementor-widget elementor-widget-eael-dual-color-header\" data-id=\"ccca712\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"eael-dual-color-header.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t<div class=\"eael-dual-header\">\n\t\t\t\t<h2 class=\"title eael-dch-title\"><span class=\"eael-dch-title-text eael-dch-title-lead lead solid-color\">Share Professor Mohand Aaid Allili<\/span> <span class=\"eael-dch-title-text\">publications with your network!<\/span><\/h2><div class=\"eael-dch-separator-wrap\"><span class=\"separator-one\"><\/span>\n\t\t\t<span class=\"separator-two\"><\/span><\/div>\t\t\t<\/div>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Welcome If needed, this section can contain some or all of the following: A large, engaging image of the university, department, or an abstract representation of the academic field can set a professional and inspiring tone. A brief welcome message or introduction that explains what visitors will find on the page. This could be a [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"open","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-4182","page","type-page","status-publish","hentry","entry"],"_links":{"self":[{"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/pages\/4182","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/comments?post=4182"}],"version-history":[{"count":1,"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/pages\/4182\/revisions"}],"predecessor-version":[{"id":4184,"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/pages\/4182\/revisions\/4184"}],"wp:attachment":[{"href":"https:\/\/cirics.uqo.ca\/en\/wp-json\/wp\/v2\/media?parent=4182"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}