A computerized method for classifying the postures of freely moving rodents is presented. The behavior of the rats was recorded on videotape by means of a camera hanging perpendicular to an open field. An automatic tracking system (10 images/sec) was used to transform the video images of postures into a binary image, thereby providing silhouettes in a computer format. The contours of these silhouettes were used for determining their characteristic features with the help of a Fourier transformation. The resulting features were classified with the help of a Kohonen network composed of 32 neurons. The four best winning neurons, rather than the usual one, were used for the classification. The resolution (11,090 distinct classes of postures), reliability (96.9%), and validity of this method were determined. With the use of the same approach, the effectiveness of this method for classifying behaviors was illustrated by analyzing grooming (247 grooming images vs. 4,950 nongrooming images). We found 15.4% false positives and 2.5% false negatives.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3758/bf03200788 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Falls and balance impairment; what and how has this been measured in adults with joint hypermobility? A scoping review.
BMC Musculoskelet Disord
January 2025
The Nick Davey Laboratory, Division of Surgery, Department of Surgery and Cancer, Faculty of Medicine, Sir Michael Uren Hub, Imperial College London, White City Campus, 86 Wood Lane, London, W12 0BZ, UK.
Background: People with joint hypermobility have excessive joint flexibility, which is more common in young women. The people with symptomatic hypermobility report poor balance and even falls. This scoping review aims to identify and map the available evidence related to balance and falling in adults with joint hypermobility to support research planning and ideas for treatment direction.
View Article and Find Full Text PDFA fuzzy logic approach to improve the sensitivity of the rapid entire body assessment method.
Int J Occup Saf Ergon
January 2025
Institute for Future (IFF), Qingdao University, People's Republic of China.
Conventional ergonomic observation methods, such as rapid entire body assessment (REBA), are limited in their sensitivity and reliability, particularly in detecting changes in input variables. This study integrates fuzzy logic with the REBA method, utilizing trapezoidal membership functions to fuzzify the input variables. The center of gravity method was employed for defuzzification, and if-then rules were formulated to enhance the REBA method.
View Article and Find Full Text PDFOccupational management of low back pain secondary to prolapsed intervertebral disc in a Malaysian healthcare worker: a case report emphasizing ergonomic intervention and risk reduction strategies.
Ind Health
January 2025
Department of Social and Preventive Medicine, Faculty of Medicine, Universiti Malaya, Malaysia.
Low back pain (LBP) is a commonly encountered medical disorder in Malaysia's primary care setting, though establishing a direct connection between LBP and the workplace environment in adults is challenging. This case presents a clinic nurse who developed LBP due to a prolapsed intervertebral disc and her clinical management from an Occupational Health Doctor perspective. Her occupational management involved a walk-through survey at an urban hospital, which identified bone marrow aspiration as her most physically demanding task.
View Article and Find Full Text PDFUsing Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed.
Sensors (Basel)
January 2025
Curtin School of Allied Health, Curtin University, Perth 6102, Australia.
In hospitals, timely interventions can prevent avoidable clinical deterioration. Early recognition of deterioration is vital to stopping further decline. Measuring the way patients position themselves in bed and change their positions may signal when further assessment is necessary.
View Article and Find Full Text PDFSleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors.
Sensors (Basel)
January 2025
Department of Information Engineering, University of Padova, 35122 Padova, Italy.
Sleep posture is a key factor in assessing sleep quality, especially for individuals with Obstructive Sleep Apnea (OSA), where the sleeping position directly affects breathing patterns: the side position alleviates symptoms, while the supine position exacerbates them. Accurate detection of sleep posture is essential in assessing and improving sleep quality. Automatic sleep posture detection systems, both wearable and non-wearable, have been developed to assess sleep quality.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!