Publikationen Digital Innovation
Unsere Mitarbeitenden im Bereich Digital Innovation sind anerkannte Experten in ihrem Fachgebiet und publizieren regelmässig wissenschaftliche Arbeiten in Form von Papers, Präsentationen und Vorträgen.
Zudem unterstützen wir Studierende, die Interesse haben, ihre Studien-, Bachelor- oder Masterarbeit im Bereich Digital Innovation zu schreiben. In Zusammenarbeit mit der OST- Fachhochschule Ostschweiz können wir Ihnen auch eine komplette Masterausbildung bei uns anbieten.
Unten finden Sie eine Auswahl der Publikationen.
Publikationen 2023
Design of Time-Encoded Spiking Neural Networks in 7-nm CMOS Technology
S. Widmer1,2,3, M. Kossel2, G. Cherubini2, S. Woźniak2, P.A. Francese2, A. Stanojevic2, M. Brändli2, K. Frick3, A. Pantazi2
Published: May 18, 2023
In biologically inspired spiking neural networks (SNNs) neurons communicate by short pulses, called spikes. SNNs have the potential to be more power efficient than artificial neural networks (ANNs), thanks to the fewer computational steps required by the spike transmission and processing, as compared to the multiply-and-accumulate (MAC) operations with wide bit-vectors usually adopted in ANNs. We present the design of two types of SNNs with integrate-and-fire dynamics and single-spike per neuron operation, where neural communication is based on synchronous time-to-first-spike (sTTFS) and time-to-first-spike (TTFS) encoding schemes. In the considered time-encoded SNNs, the information is carried by the timing of the spikes with respect to a reference time. In 7nm CMOS technology both designs are synthesized as VHDL-based random-logic-macros (RLMs) and compared to an equivalent ANN design in terms of power consumption, latency and silicon area, using the Iris data set for inference. A cost function expressed as a product of energy consumption and silicon area is introduced to compare the three network designs. With respect to this cost function, it turns out that the SNN-TTFS implemented for the considered classification task outperforms the ANN used as baseline model.
1RhySearch, Werdenbergstr. 4, 9471 Buchs, Switzerland
2IBM Research GmbH, Säumerstr. 4, 8803 Rüschlikon, Switzerland
3OST—University of Applied Sciences, Bogenstr. 7, 9000 St. Gallen, Switzerland
Work-in-Progress—Effects of Attention Guidance on Virtual Reality Training for an Industrial Assembly Task
J. Gisler1, D. Dedic1, V. Holzwarth2, A. Kunz1
Published: June 17, 2023
One of the main objectives of Virtual Training Environments (VTEs) for industrial training is to train workers for a real world task. Prior work identified a multitude of factors influencing a VTE’s effectiveness. In this work-in-progress paper, we add to this body of research by evaluating the effect of attention guidance (AG) on a VTE’s effectiveness. In a controlled between-subject design pilot study with 42 participants, participants were trained in a VTE either with or without AG. Subsequently, learning transfer was assessed in a Real-World Evaluation (RWE). Our findings indicate that, while not necessary for a VTE’s efficacy, AG appears to be a substantial factor in a VTE’s effectiveness.
1ETH Zurich, Rämistr. 101, 8092 Zurich, Switzerland
2RhySearch, Werdenbergstr. 4, 9471 Buchs, Switzerland
How to effectively use distributed ledger technology in supply chain management?
A. Herbe1, Z. Estermann2, V. Holzwarth3, J. vom Brocke1
Published: June 07, 2023
Distributed Ledger Technology (DLT) refers to multi-party systems that enables saving encrypted data across a peer-to-peer network of nodes, without central authority. While DLT applications have been mainly studied in finance, we conduct empirical research on DLT application in supply chain management, combining theory testing and theory elaborating case research. Applying the Theory of Affordance Actualisation, we identify five DLT affordances: (1) verify product origin and history, (2) exchange data on digital product models, (3) track and trace products’ logistics, (4) simplify supply chain finance, and (5) automate payments. We identify and evaluate these affordances and also outline how these affordances can be actualised. We contribute to the discourse of DLT value creation and provide practical guidance to assess DLT potential in supply chains. We integrate our findings into the academic discussion on collaboration in viable, intertwined supply networks.
1University of Liechtenstein, Fürst-Franz-Josef-Strasse, 9490 Vaduz, Liechtenstein
2University of St. Gallen (HSG), Dufourstrasse 50, 9000 St. Gallen, Switzerland
3RhySearch, Werdenbergstr. 4, 9471 Buchs, Switzerland
Publikationen 2022
Virtual Reality Extension for Digital Twins of Machine Tools
Valentin Holzwarth2, 3, Christian Hirt1, Joy Gisler1, Andreas Kunz1
Published: April 27, 2022
Digital twins (DTs) provide numerous opportunities for value creation in manufacturing. Services enabled by DTs include remote monitoring of assets’ conditions and predictive maintenance. In this paper, we introduce novel, previously unexplored services based on a fully virtualized machine tool, which are targeted at increasing machine operators’ productivity. This allows conducting procedures, such as operator training at a virtual machine tool, which results in the real machine tool being available for value adding activities. Beyond operator training, we envision further potential applications of the virtual machine tool including the run-in of new processes and collision detection.
1 Innovation Center Virtual Reality (ICVR), ETH Zurich, 8092, Zurich, Switzerland
2 Institute of Information Systems, University of Liechtenstein, 9490, Vaduz, Liechtenstein
3RhySearch, Werdenbergstr. 4, 9471 Buchs, Switzerland
Unsere Website verwendet Cookies, damit wir die Page fortlaufend verbessern und Ihnen ein optimiertes Besucher-Erlebnis ermöglichen können. Wenn Sie auf dieser Webseite weiterlesen, erklären Sie sich mit der Verwendung von Cookies einverstanden.
Weitere Informationen zu Cookies finden Sie in unserer Datenschutzerklärung.
Wenn Sie das Setzen von Cookies z.B. durch Google Analytics unterbinden möchten, können Sie dies mithilfe dieses Browser Add-Ons einrichten.