talk update

ComNets-Bremen · Aug 10, 2023 · 66d951f · 66d951f
1 parent 0ee2f26
commit 66d951f
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 11 deletions.
diff --git a/_includes/talks.html b/_includes/talks.html
@@ -16,17 +16,7 @@
                     <div class="content">
 
 
-                        <h2>On indoor localization: a TinyML-based classification approach | Prof. Diego Méndez Chaves</h2>
-                        <p>Aug 03, 2023 | 4:00 PM CET</p>
-
-                        <p><strong>About Topic:</strong> 
-                            Positioning systems have gained paramount importance for many different productive sector; however, traditional systems such as Global Positioning System (GPS) have failed to offer accurate and scalable solutions for indoor positioning requirements. Nowadays, alternative solutions such as fingerprinting allow the recognition of the characteristic signature of a location based on RF signal acquisition. In our work, a machine learning (ML) approach is selected in order to classify the RSSI information acquired by multiple scanning stations from TAG broadcasting messages. TinyML has been considered for this project, as it is a rapidly growing technological paradigm that aims to assist the design and implementation of ML mechanisms in resource-constrained embedded devices. This talk presents the design, implementation, and deployment of embedded devices capable of communicating and sending information to a central system that determines the location of objects in a defined environment. A neural network (deep learning) is trained and deployed on the edge, allowing the multiple external error factors that affect the accuracy of traditional position estimation algorithms to be considered. Edge Impulse is used as the main platform for data standardization, pre-processing, model training, evaluation, and deployment.
-                        </p>
-
-                        <p><strong>About Speaker:</strong> 
-                            Diego Méndez Chaves is an Associate Professor in the Department of Electronics Engineering at the Pontificia Universidad Javeriana, Bogotá, Colombia. He received his Ph.D (2012) and his M.Sc. (2011) in Computer Science from the University of South Florida, Tampa FL, USA, his M.E. (2008) from the Universidad de Los Andes, Bogotá, Colombia, and his B.E (2005) in Electronics Engineering from the Universidad Nacional, Bogotá, Colombia. Diego’s research interests include Internet of Things (IoT), embedded systems, wireless sensor networks, participatory sensing, digital systems design, operating systems and high-level systems design. He is currently a Research Associate at the T/ICT4D Lab of the International Centre for Theoretical Physics (ICTP) in Trieste, Italy.
-                        </p>
-
+                    <h2>Stay Tuned</h2>    
                     </div>
 
                     {% for post in site.posts %}

diff --git a/_posts/2017-06-24-past_talks.md b/_posts/2017-06-24-past_talks.md
@@ -3,6 +3,19 @@ layout: post
 title: "Past Seminars"
 date: 2017-06-09 12:00:00 -0500
 ---
+<h2>On indoor localization: a TinyML-based classification approach | Prof. Diego Méndez Chaves</h2>
+<p>Aug 03, 2023 | 4:00 PM CET</p>
+
+<p><strong>About Topic:</strong> 
+    Positioning systems have gained paramount importance for many different productive sector; however, traditional systems such as Global Positioning System (GPS) have failed to offer accurate and scalable solutions for indoor positioning requirements. Nowadays, alternative solutions such as fingerprinting allow the recognition of the characteristic signature of a location based on RF signal acquisition. In our work, a machine learning (ML) approach is selected in order to classify the RSSI information acquired by multiple scanning stations from TAG broadcasting messages. TinyML has been considered for this project, as it is a rapidly growing technological paradigm that aims to assist the design and implementation of ML mechanisms in resource-constrained embedded devices. This talk presents the design, implementation, and deployment of embedded devices capable of communicating and sending information to a central system that determines the location of objects in a defined environment. A neural network (deep learning) is trained and deployed on the edge, allowing the multiple external error factors that affect the accuracy of traditional position estimation algorithms to be considered. Edge Impulse is used as the main platform for data standardization, pre-processing, model training, evaluation, and deployment.
+</p>
+
+<p><strong>About Speaker:</strong> 
+    Diego Méndez Chaves is an Associate Professor in the Department of Electronics Engineering at the Pontificia Universidad Javeriana, Bogotá, Colombia. He received his Ph.D (2012) and his M.Sc. (2011) in Computer Science from the University of South Florida, Tampa FL, USA, his M.E. (2008) from the Universidad de Los Andes, Bogotá, Colombia, and his B.E (2005) in Electronics Engineering from the Universidad Nacional, Bogotá, Colombia. Diego’s research interests include Internet of Things (IoT), embedded systems, wireless sensor networks, participatory sensing, digital systems design, operating systems and high-level systems design. He is currently a Research Associate at the T/ICT4D Lab of the International Centre for Theoretical Physics (ICTP) in Trieste, Italy.
+</p>
+
+<a href="https://www.youtube.com/live/KC5f8rxeQ_0?feature=share" target="_blank">*Watch the Seminar*</a>
+<hr />
 
 <h2>Surprises Included: On Experiences with Outdoor Experiments | Lars Wolf</h2>
 <p>July 06, 2023 | 4:00 PM CET</p>