{"id":83,"date":"2025-04-10T14:22:51","date_gmt":"2025-04-10T14:22:51","guid":{"rendered":"https:\/\/www.protect-sps.eu\/?page_id=83"},"modified":"2026-03-02T08:47:35","modified_gmt":"2026-03-02T08:47:35","slug":"publications","status":"publish","type":"page","link":"https:\/\/www.protect-sps.eu\/?page_id=83","title":{"rendered":"Publications"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\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
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Beam-Book Precoding of a 1-bit Reconfigurable Intelligent Surface at 5 GHz for Beam Steering<\/strong><\/h4>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Status: In preparation<\/strong><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Reflective intelligent surfaces (RIS) are programmable devices capable of steering an impinging electromagnetic wave toward a desired direction (i.e., without strictly following Snell’s law), potentially providing significant gains in next-generation wireless communications (6G). RISs can support both established and emerging applications, including radar\/sensing and coverage extension in non-line-of-sight (NLOS) scenarios. Many of these applications rely on the ability of the RIS to steer the beam toward a known direction; accordingly, our aim is to provide an analytical beam-book design to achieve this goal. In this paper, we focus on the open-source 1-bit RIS design operating around 5 GHz and propose an analytical method to generate a beam book, enabling fast beam steering without online optimization. The beam-book configurations are obtained from a closed-form phase model (2D and 3D) and then quantized to the two available phase states. We validate the proposed approach through laboratory measurements using a prototype of the open-source RIS. Experimental results show that the beam-book entry corresponding to the receiver direction consistently maximizes the received signal and provides significant RIS-assisted gains and the theoretical radiation patterns closely match the experimental measures.<\/p>\t\t\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
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
CoBA: Integrated Deep Learning Model for Reliable Low-Altitude UAV Classification in mmWave Radio Networks<\/strong><\/h4>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Status: Accepted for publication at ICC 2026<\/strong><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Uncrewed Aerial Vehicles (UAVs) are increasingly used in civilian and industrial applications, making secure low-altitude operations crucial. In dense mmWave environments, accurately classifying low-altitude UAVs as either inside authorized or restricted airspaces remains challenging, requiring models that handle complex propagation and signal variability. This paper proposes a deep learning model, referred to as CoBA, which stands for integrated Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Attention which leverages Fifth Generation (5G) millimeter-wave (mmWave) radio measurements to classify UAV operations in authorized and restricted airspaces at low altitude. The proposed CoBA model integrates convolutional, bidirectional recurrent, and attention layers to capture both spatial and temporal patterns in UAV radio measurements. To validate the model, a dedicated dataset is collected using the 5G mmWave network at TalTech, with controlled low altitude UAV flights in authorized and restricted scenarios. The model is evaluated against conventional ML models and a fingerprinting-based benchmark. Experimental results show that CoBA achieves superior accuracy, significantly outperforming all baseline models and demonstrating its potential for reliable and regulated UAV airspace monitoring.<\/p>\t\t\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
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Enhanced Forest Sound Classification Dataset: EFSC-24<\/strong><\/h4>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Status: Published<\/a><\/strong><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Forest sound classification is essential for monitoring forest ecosystems and promoting sustainable forest management. This paper introduces an Enhanced Forest Sound Classification Dataset 2024 (EFSC-24) and proposes a novel stacking model to classify the forest sounds. The proposed model’s performance is evaluated and compared with benchmark algorithms such as K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Random Forest, and XGBoost. for both FSC-22 and EFSC-24. The comparison of proposed stacking model with benchmark models exhibits performance gains of up to 58%.<\/p>\t\t\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
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\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":"
Beam-Book Precoding of a 1-bit Reconfigurable Intelligent Surface at 5 GHz for Beam Steering Status: In preparation Reflective intelligent surfaces (RIS) are programmable devices capable of steering an impinging electromagnetic wave toward a desired direction (i.e., without strictly following Snell’s law), potentially providing significant gains in next-generation wireless communications (6G). RISs can support both established […]<\/p>\n","protected":false},"author":3,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"elementor_header_footer","meta":{"footnotes":""},"class_list":["post-83","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=\/wp\/v2\/pages\/83","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=83"}],"version-history":[{"count":20,"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=\/wp\/v2\/pages\/83\/revisions"}],"predecessor-version":[{"id":414,"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=\/wp\/v2\/pages\/83\/revisions\/414"}],"wp:attachment":[{"href":"https:\/\/www.protect-sps.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=83"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}