AHAlex Hanneman

Alex Hanneman

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Alex Hanneman has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Soft Error Assessment of Attitude Estimation Algorithms Running on Resource-Constrained Devices Under Neutron Radiation

    by Jonas Gava, Tarso Sartori, Alex Hanneman, Rafael Garibotti, Fernando Moraes, Ney Calazans, Hassen Fourati, Rodrigo Possamai Bastos, Ricardo Reis, Luciano Ost

    There is a growing incorporation of unmanned aerial vehicles (UAVs) within remote and urban environments due to their versatility and ability to access hard-to-reach and/or congested places. UAVs offer low-cost solutions for many applications, including healthcare (e.g., medical supplies delivery) and surveillance during public events, protests, or emergencies (e.g., nuclear accident). However, drone utilisation in urban areas often relies on strict regulations to ensure safe and responsible operation. UAVs are subject to radiation-induced soft errors, and identifying the most vulnerable software and hardware components to radiation exposure is a advisable task, which is difficult to undertake. An essential task to UAVs correct operation is attitude estimation. This paper assesses the soft error reliability of three attitude estimation algorithms running on two resource-constrained microprocessors under neutron radiation. Results suggest that the extended Kalman filter (EKF) algorithm provides the best mean work to failure result for critical fault events, which is about 3× more than the indirect Kalman filter (IKF) and 1.5× more w.r.t. the novel quaternion Kalman filter algorithm (NQKF).


  • A Lightweight Mitigation Technique for Resource- Constrained Devices Executing DNN Inference Models Under Neutron Radiation

    by Jonas Gava, Alex Hanneman, Geancarlo Abich, Rafael Garibotti, Sergio Cuenca-Asensi, Rodrigo Possamai Bastos, Ricardo Reis, Luciano Ost

    Deep neural network (DNN) models are being deployed in safety-critical embedded devices for object identification, recognition, and even trajectory prediction. Optimised versions of such models, in particular the convolutional ones, are becoming increasingly common in resource-constrained edge-computing devices (e.g., sensors, drones), which typically rely on reduced memory footprint, low power budget and low-performance microprocessors. DNN models are prone to radiation-induced soft errors, and tackling their occurrence in resource-constrained devices is a mandatory and substantial challenge. While traditional replication-based soft error mitigation techniques will likely account for a reasonable performance penalty, hardware solutions are even more costly. To undertake this almost contradictory challenge, this work evaluates the efficiency of a lightweight software-based mitigation technique, called Register Allocation Technique (RAT), when applied to a convolutional neural network (CNN) model running on two commercial Arm microprocessors (i.e., Cortex-M4 and M7) under the effects of neutron radiation. Gathered results obtained from two neutron radiation campaigns suggest that RAT can reduce the number of critical faults in the CNN model running on both Arm Cortex-M microprocessors. Results also suggest that the SDC FIT rate of the RAT-hardened CNN model can be reduced in up to 83% with a runtime overhead of 32%.


  • Novel Low Memory Footprint DNN Models for Edge Classification of Surgeons’ Postures

    by Alex Hanneman, Terry Fawden, Marco Branciforte, Maria Celvisia Virzì, Esther L. Moss, Luciano Ost, Massimiliano Zecca

    Skill assessment is fundamental to enhance current laparoscopic surgical training and reduce the incidence of musculoskeletal injuries from performing these procedures. Recently, deep neural networks (DNNs) have been used to improve human posture and surgeons’ skills training. While they work well in lab, they normally require significant computational power which makes it impossible to use them on edge devices. This paper presents two low memory footprint DNN models used for classifying laparoscopic surgical skill levels at the edge. Trained models were deployed on three Arm Cortex-M processors using the X-Cube-AI and TensorFlow Lite Micro (TFLM) libraries. Results show that the CUBE-AI-based models give the best relative performance, memory footprint, and accuracy trade-offs when executed on the Cortex-M7.