Journal: PLoS ONE

Article Title: Criterion validity of the ActiGraph and activPAL in classifying posture and motion in office-based workers: A cross-sectional laboratory study

doi: 10.1371/journal.pone.0252659

Figure Lengend Snippet: Number (%) of tasks correctly classified by the activPAL and ActiGraph in repeated measurements.

Article Snippet: The activPAL micro (PAL Technologies Ltd, Glasgow, Scotland, UK) is a small, lightweight, thigh-worn accelerometer/inclinometer that has been designed to quantify periods of an individual`s sedentary and upright positions and daily activities using proprietary algorithms [ – ].

Techniques:

Journal: PLoS ONE

Article Title: Criterion validity of the ActiGraph and activPAL in classifying posture and motion in office-based workers: A cross-sectional laboratory study

doi: 10.1371/journal.pone.0252659

Figure Lengend Snippet: Percentages of correctly classified tasks for the activPAL and ActiGraph considering all individual measurements (2A) and percentages of correctly classified tasks during both experimental visits, i.e., on repeated occasions (2B). Individual tasks were clustered into sitting (N = 11), standing (N = 5), stepping (N = 5) and postural transitions (N = 3).

Article Snippet: The activPAL micro (PAL Technologies Ltd, Glasgow, Scotland, UK) is a small, lightweight, thigh-worn accelerometer/inclinometer that has been designed to quantify periods of an individual`s sedentary and upright positions and daily activities using proprietary algorithms [ – ].

Techniques:

Journal: PLoS ONE

Article Title: Criterion validity of the ActiGraph and activPAL in classifying posture and motion in office-based workers: A cross-sectional laboratory study

doi: 10.1371/journal.pone.0252659

Figure Lengend Snippet: Angle measurements for the ActiGraph (3A) and activPAL (3B) using a protractor. The picture in the middle shows the starting position with the devices placed parallel to the floor and the protractor scale reading 0°, representing sitting. The areas in white and grey represent the coded position and angle ranges relative to the horizontal. White = sitting, dark grey = standing, light grey = postural transition (sitting to standing or vice versa). The arrows show the direction in which the devices were moved. The double arrow in 3A shows that the coded position was independent from the direction in which the monitor was moved. The two arrows in 3B highlight differences in the coded posture and postural transition, depending in which direction the monitor was moved.

Article Snippet: The activPAL micro (PAL Technologies Ltd, Glasgow, Scotland, UK) is a small, lightweight, thigh-worn accelerometer/inclinometer that has been designed to quantify periods of an individual`s sedentary and upright positions and daily activities using proprietary algorithms [ – ].

Techniques:

Journal: Journal for the measurement of physical behaviour

Article Title: CHAP-Adult: A Reliable and Valid Algorithm to Classify Sitting and Measure Sitting Patterns Using Data From Hip-Worn Accelerometers in Adults Aged 35+

doi: 10.1123/jmpb.2021-0062

Figure Lengend Snippet: STROBE diagram for data used to train and validate the CHAP-Adult algorithm. ACT = Adult Changes in Thought study; AusDiab = Australian Diabetes, Obesity, and Lifestyle study; CHAP = Convolutional Neural Network Hip Accelerometer Posture.

Article Snippet: Using a combined Convolutional Neural Network (CNN) + bidirectional long shortterm memory network (BiLSTM) model architecture in a sample of older adults, we developed a novel method for predicting sitting postures from hip-worn accelerometer data (e.g., ActiGraph) in older adults by training against concurrently thigh-worn activPAL inclinometers.

Techniques:

Journal: Journal for the measurement of physical behaviour

Article Title: CHAP-Adult: A Reliable and Valid Algorithm to Classify Sitting and Measure Sitting Patterns Using Data From Hip-Worn Accelerometers in Adults Aged 35+

doi: 10.1123/jmpb.2021-0062

Figure Lengend Snippet: Accuracy metrics for sitting (a) and postural transitions (b) for CHAP-Adult using the ACT and AusDiab combined for-validation sample (n = 419). ACT = Adult Changes in Thought study; AusDiab = Australian Diabetes, Obesity, and Lifestyle study; CHAP = Convolutional Neural Network Hip Accelerometer Posture.

Article Snippet: Using a combined Convolutional Neural Network (CNN) + bidirectional long shortterm memory network (BiLSTM) model architecture in a sample of older adults, we developed a novel method for predicting sitting postures from hip-worn accelerometer data (e.g., ActiGraph) in older adults by training against concurrently thigh-worn activPAL inclinometers.

Techniques: Biomarker Discovery