CSEM Scientific & Technical Articles
Permanent URI for this collection
Browse
Recent Submissions
Item Single-cell real-time analysis modules(2025) Aeby, E.; Cristofolini, P.; Fonta, C.; Markocic, M.; Cattenoz, R.; Glushkov, E.; Boudoire, F.; Loussert-Fonta, C.; Zhou, J.; Chen, L.; Blache, M.; Pereira de Carvalho, M.; Cattaneo, S.; Boder-Pasche, S.; Valentin, T.; Weder, G.This report focuses on single-cell real-time analysis modules (SCREAM) integrating fluorescence readout and sorting, microlens arrays for improved imaging and high-throughput viable RNA extraction. Results: (1) software enabling full real-time signal analysis on a field-programmable gate array (FPGA), user-friendly via a python-based graphical user interface (GUI) and implemented sorting capabilities; (2) microlens arrays (MLAs) produced on glass substrates, and integrated on multi-well plates, or micro-stereolithography (µSLA) printed microfluidic chips, unifying novelty in both application and technology; (3) workflow for high-throughput, viable RNA extraction via cell squeezing. Bulk measurements indicate the presence of extracted RNA from viable cells. Overall, SCREAM offers modular components for fluorescent detection and analysis, micro-optics, and viable, high-throughput single-cell RNA sequencing (SCRNA-seq), adaptable to diverse life sciences applications. Results and discussionItem Bioimpedance and biopotential monitoring with cooperative-sensor integrated circuit(2025) Sporrer, B.; Chételat, O.; Fivaz, A.; Besse, D.This work introduces a cooperative sensor platform based on a custom integrated circuit that enables combined bioimpedance and biopotential monitoring for applications such as cardiac, neurological, and respiratory assessment. The system integrates multiple electrodes connected to the same 2-wire parallel bus with low interference with the measured signals. Initial results demonstrate correct operation, low noise, and strong potential for future clinical and wearable use.Item Fabricating 3D structures using spray coating(2025) Pétremand, Y.; Grétillat, J.; Schildknecht, J.; Dubochet, O.; Overstolz, T.Micro-electro-mechanical systems (MEMS) are widely used in biomedical and life science applications. Their fabrication traditionally relies on a layer-by-layer process performed on planar substrates. However, MEMS devices inherently feature three-dimensional architectures, for which planar processing can impose significant limitations. Spray coating techniques offer a viable solution to overcome these constraints by enabling uniform coating and patterning of non-planar surfaces. The acquisition of a stand-alone spray coating tool significantly expands CSEM’s fabrication capabilities, opening new opportunities for the development of advanced devices, and the exploration of novel products and research projects.Item Vision-to-inertial measurement unit knowledge transfer for wearable action recognition: Application to fall detection(2025) Soltani, R.; Vuagniaux, R.; Saeedi, S.; El Achkar, C. M.; Türetken, E.; Dia, M.; Lemay, M.; Maamari, N.Human activity recognition using wearable sensors is often limited by the availability and diversity of inertial data, especially for rare or safety-critical events. Fall detection systems are a prominent example, as real fall recordings from older adults are scarce and difficult to collect. To address this challenge, we propose a cross-modal approach that transfers knowledge from vision to wearables by reconstructing 3D human poses from video and generating realistic synthetic inertial measurement unit (IMU) signals. The models are pretrained and fine-tuned on publicly available datasets to estimate accurate world-frame full-body 3D poses from videos and use them to simulate IMU signals. The proposed IMU estimator achieves low median errors (0.02 g and 31.9 d/s), demonstrating a close match between simulated and real inertial signals. For fall detection, when used for impact detection, the simulated IMUs achieve 100% sensitivity and specificity. Converting detected impacts into confirmed falls is more conservative, with a fall-confirmation sensitivity of 40% while specificity remains 100%. Overall, these results show that synthetic IMU signals extracted from real-world video provide high-fidelity motion and impact information that can complement wearable datasets. Beyond fall detection, this vision-to-IMU knowledge transfer approach supports more robust and scalable IMU-based action recognition across a wide range of human activities.Item Silicon solar low-power perception platform(2025) Ben Salah, M. I.; Senaud, L.-L.; Dherse, A.; Ferragni, A.; Koller, J.-M.; Geissbühler, J.SCALPEL is a powerful, yet energy efficient, wearable platform that combines ultra-low power electronics with embedded Artificial Intelligence (AI) based on the latest ARM Ethos-U55 Neural Processing Unit. Powered by CSEM’s high-efficiency interdigitated back contact (IBC) photovoltaic (PV) technology and running the ultra-low power CSEM Real-Time Operating System (RTOS), it integrates multimodal sensors: vision, audio, ranging, and geotagging to enable low latency and privacy preserving interaction. The demonstrator and its components endured extensive characterization and on-field campaign, enabling full autonomy or significantly extended lifetime. A keyword spotting application illustrates the platform’s efficiency, operating autonomously using the energy harvested by the PV module and a battery.