1
|
Passias A, Tsakalos KA, Kansizoglou I, Kanavaki AM, Gkrekidis A, Menychtas D, Aggelousis N, Michalopoulou M, Gasteratos A, Sirakoulis GC. A Biologically Inspired Movement Recognition System with Spiking Neural Networks for Ambient Assisted Living Applications. Biomimetics (Basel) 2024; 9:296. [PMID: 38786506 PMCID: PMC11117771 DOI: 10.3390/biomimetics9050296] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2023] [Revised: 02/20/2024] [Accepted: 03/12/2024] [Indexed: 05/25/2024] Open
Abstract
This study presents a novel solution for ambient assisted living (AAL) applications that utilizes spiking neural networks (SNNs) and reconfigurable neuromorphic processors. As demographic shifts result in an increased need for eldercare, due to a large elderly population that favors independence, there is a pressing need for efficient solutions. Traditional deep neural networks (DNNs) are typically energy-intensive and computationally demanding. In contrast, this study turns to SNNs, which are more energy-efficient and mimic biological neural processes, offering a viable alternative to DNNs. We propose asynchronous cellular automaton-based neurons (ACANs), which stand out for their hardware-efficient design and ability to reproduce complex neural behaviors. By utilizing the remote supervised method (ReSuMe), this study improves spike train learning efficiency in SNNs. We apply this to movement recognition in an elderly population, using motion capture data. Our results highlight a high classification accuracy of 83.4%, demonstrating the approach's efficacy in precise movement activity classification. This method's significant advantage lies in its potential for real-time, energy-efficient processing in AAL environments. Our findings not only demonstrate SNNs' superiority over conventional DNNs in computational efficiency but also pave the way for practical neuromorphic computing applications in eldercare.
Collapse
Affiliation(s)
- Athanasios Passias
- Department of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi, Greece; (A.P.); (K.-A.T.)
| | - Karolos-Alexandros Tsakalos
- Department of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi, Greece; (A.P.); (K.-A.T.)
| | - Ioannis Kansizoglou
- Department of Production and Management Engineering, Democritus University of Thrace, 67100 Xanthi, Greece; (I.K.); (A.G.)
| | - Archontissa Maria Kanavaki
- School of Physical Education and Sport Science, Democritus University of Thrace, 69100 Komotini, Greece; (A.M.K.); (A.G.); (D.M.); (N.A.); (M.M.)
| | - Athanasios Gkrekidis
- School of Physical Education and Sport Science, Democritus University of Thrace, 69100 Komotini, Greece; (A.M.K.); (A.G.); (D.M.); (N.A.); (M.M.)
| | - Dimitrios Menychtas
- School of Physical Education and Sport Science, Democritus University of Thrace, 69100 Komotini, Greece; (A.M.K.); (A.G.); (D.M.); (N.A.); (M.M.)
| | - Nikolaos Aggelousis
- School of Physical Education and Sport Science, Democritus University of Thrace, 69100 Komotini, Greece; (A.M.K.); (A.G.); (D.M.); (N.A.); (M.M.)
| | - Maria Michalopoulou
- School of Physical Education and Sport Science, Democritus University of Thrace, 69100 Komotini, Greece; (A.M.K.); (A.G.); (D.M.); (N.A.); (M.M.)
| | - Antonios Gasteratos
- Department of Production and Management Engineering, Democritus University of Thrace, 67100 Xanthi, Greece; (I.K.); (A.G.)
| | - Georgios Ch. Sirakoulis
- Department of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi, Greece; (A.P.); (K.-A.T.)
| |
Collapse
|
2
|
Pignet AL, Kranzl A, Hecker A, Weigel G, Kamolz LP, Girsch W. Kinematic Effects of Derotational Osteotomy of the Humerus in Patients with Internal Shoulder Contracture Secondary to Erb's Palsy-A Retrospective Cohort Study. J Clin Med 2024; 13:2759. [PMID: 38792301 PMCID: PMC11121948 DOI: 10.3390/jcm13102759] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2024] [Revised: 04/28/2024] [Accepted: 05/05/2024] [Indexed: 05/26/2024] Open
Abstract
Background: Internal rotation contractures of the shoulder are common sequelae of conservatively treated obstetric brachial plexus palsy (OBPP) with incomplete spontaneous neurological recovery. Humerus derotation osteotomy has been suggested as a possible treatment option to improve arm positioning. However, consensus as to whether humerus derotation osteotomy can successfully restore limb function is missing. Methods: In the present controlled cohort study, we aimed at analyzing global upper extremity kinematics with a 3D-video analysis system in children with shoulder internal rotation contractures secondary to OBPP before, and one year after, humerus derotation osteotomy. Patients under 18 years of age that presented to our center with conservatively treated internal rotation contractures of the shoulder and subsequently underwent humerus derotation osteotomy were included. The unimpaired arm served as a respective control. Results: Pre-operatively, all patients showed severe internal rotation contractures of the shoulder of almost 60° at rest. At the follow-up, the position of the shoulder at rest was greatly shifted to 9° of internal rotation. The patients showed statistically significant improvement in maximum external rotation and abduction of the shoulder, as well as in maximum flexion of the elbow, and the range of motion of pro/supination. The maximum internal rotation of the shoulder, however, was diminished after the osteotomy. Conclusions: Our data indicated that derotational osteotomy is a promising procedure which can be used to correct for internal rotation contractures secondary to OBPP. Moreover, 3D-video analysis proved to be a useful tool that supplies the surgeon with both precise information about the degree of distortion pre-operatively, thus helping to decide on the amount of correction, and secondly, a measurement of the post-operative gain in upper extremity function.
Collapse
Affiliation(s)
- Anna-Lisa Pignet
- Division of Plastic, Aesthetic and Reconstructive Surgery, Department of Surgery, Medical University of Graz, 8036 Graz, Austria (W.G.)
| | - Andreas Kranzl
- Laboratory for Gait and Movement Analysis, Orthopaedic Hospital Vienna-Speising, 1130 Vienna, Austria
| | - Andrzej Hecker
- Division of Plastic, Aesthetic and Reconstructive Surgery, Department of Surgery, Medical University of Graz, 8036 Graz, Austria (W.G.)
| | - Gerlinde Weigel
- Austrian Armed Forces, Medical Center East, Medical Facility Vienna, 1210 Vienna, Austria
| | - Lars-Peter Kamolz
- Division of Plastic, Aesthetic and Reconstructive Surgery, Department of Surgery, Medical University of Graz, 8036 Graz, Austria (W.G.)
| | - Werner Girsch
- Division of Plastic, Aesthetic and Reconstructive Surgery, Department of Surgery, Medical University of Graz, 8036 Graz, Austria (W.G.)
| |
Collapse
|
3
|
Weller HI, Hiller AE, Lord NP, Van Belleghem SM. recolorize: An R package for flexible colour segmentation of biological images. Ecol Lett 2024; 27:e14378. [PMID: 38361466 DOI: 10.1111/ele.14378] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Revised: 12/18/2023] [Accepted: 01/04/2024] [Indexed: 02/17/2024]
Abstract
Colour pattern variation provides biological information in fields ranging from disease ecology to speciation dynamics. Comparing colour pattern geometries across images requires colour segmentation, where pixels in an image are assigned to one of a set of colour classes shared by all images. Manual methods for colour segmentation are slow and subjective, while automated methods can struggle with high technical variation in aggregate image sets. We present recolorize, an R package toolbox for human-subjective colour segmentation with functions for batch-processing low-variation image sets and additional tools for handling images from diverse (high-variation) sources. The package also includes export options for a variety of formats and colour analysis packages. This paper illustrates recolorize for three example datasets, including high variation, batch processing and combining with reflectance spectra, and demonstrates the downstream use of methods that rely on this output.
Collapse
Affiliation(s)
- Hannah I Weller
- Department of Ecology, Evolution, and Organismal Biology, Brown University, Providence, Rhode Island, USA
- Helsinki Institute of Life Sciences, University of Helsinki, Helsinki, Finland
| | - Anna E Hiller
- Museum of Natural Science and Department of Biological Sciences, Louisiana State University, Baton Rouge, Louisiana, USA
| | - Nathan P Lord
- Department of Entomology, Louisiana State University Agricultural Center, Baton Rouge, Louisiana, USA
| | | |
Collapse
|
4
|
Ino T, Samukawa M, Ishida T, Wada N, Koshino Y, Kasahara S, Tohyama H. Validity of AI-Based Gait Analysis for Simultaneous Measurement of Bilateral Lower Limb Kinematics Using a Single Video Camera. SENSORS (BASEL, SWITZERLAND) 2023; 23:9799. [PMID: 38139644 PMCID: PMC10747245 DOI: 10.3390/s23249799] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Revised: 12/02/2023] [Accepted: 12/12/2023] [Indexed: 12/24/2023]
Abstract
Accuracy validation of gait analysis using pose estimation with artificial intelligence (AI) remains inadequate, particularly in objective assessments of absolute error and similarity of waveform patterns. This study aimed to clarify objective measures for absolute error and waveform pattern similarity in gait analysis using pose estimation AI (OpenPose). Additionally, we investigated the feasibility of simultaneous measuring both lower limbs using a single camera from one side. We compared motion analysis data from pose estimation AI using video footage that was synchronized with a three-dimensional motion analysis device. The comparisons involved mean absolute error (MAE) and the coefficient of multiple correlation (CMC) to compare the waveform pattern similarity. The MAE ranged from 2.3 to 3.1° on the camera side and from 3.1 to 4.1° on the opposite side, with slightly higher accuracy on the camera side. Moreover, the CMC ranged from 0.936 to 0.994 on the camera side and from 0.890 to 0.988 on the opposite side, indicating a "very good to excellent" waveform similarity. Gait analysis using a single camera revealed that the precision on both sides was sufficiently robust for clinical evaluation, while measurement accuracy was slightly superior on the camera side.
Collapse
Affiliation(s)
- Takumi Ino
- Graduate School of Health Sciences, Hokkaido University, Sapporo 0600812, Japan;
- Department of Physical Therapy, Faculty of Health Sciences, Hokkaido University of Science, Sapporo 0068585, Japan
| | - Mina Samukawa
- Faculty of Health Sciences, Hokkaido University, Sapporo 0600812, Japan
| | - Tomoya Ishida
- Faculty of Health Sciences, Hokkaido University, Sapporo 0600812, Japan
| | - Naofumi Wada
- Department of Information and Computer Science, Faculty of Engineering, Hokkaido University of Science, Sapporo 0068585, Japan;
| | - Yuta Koshino
- Faculty of Health Sciences, Hokkaido University, Sapporo 0600812, Japan
| | - Satoshi Kasahara
- Faculty of Health Sciences, Hokkaido University, Sapporo 0600812, Japan
| | - Harukazu Tohyama
- Faculty of Health Sciences, Hokkaido University, Sapporo 0600812, Japan
| |
Collapse
|