scholarly journals Two-Step k-means Clustering Based Information Entropy for Detecting Environmental Barriers Using Wearable Sensor

Author(s):  
Bogyeong Lee ◽  
Hyunsoo Kim

Walking is the most basic means of transportation. Therefore, continuous management of the walking environment is very important. In particular, the identification of environmental barriers that can impede walkability is the first step in improving the pedestrian experience. Current practices for identifying environmental barriers (e.g., expert investigation and survey) are time-consuming and require additional human resources. Hence, we have developed a method to identify environmental barriers based on information entropy considering that every individual behaves differently in the presence of external stimuli. The behavioral data of the gait process were recorded for 64 participants using a wearable sensor. Additionally, the data were classified into seven gait types using two-step k-means clustering. It was observed that the classified gaits create a probability distribution for each location to calculate information entropy. The values of calculated information entropy showed a high correlation in the presence or absence of environmental barriers. The results obtained facilitated the continuous monitoring of environmental barriers generated in a walking environment.

Author(s):  
Bogyeong Lee ◽  
Sungjoo Hwang ◽  
Hyunsoo Kim

The enhancement of physical activity is highly correlated with the conditions of the built environment. Walking is considered to be a fundamental daily physical activity, which requires an appropriate environment. Therefore, the barriers of the built environment should be identified and addressed. Barriers can act as external stimuli for pedestrians, so pedestrians may diversely respond to them. Based on this consideration, this study examines the feasibility of information-entropy-based behavioral analysis for the detection of environmental barriers. The physical responses of pedestrians were collected using an inertial measurement unit (IMU) sensor in a smartphone. After the acquired data were converted to behavioral probability distributions, the information entropy of each grid cell was calculated. The grid cells whereby the participants indicated that environmental barriers were present yielded relatively high information entropy values. The findings of this study will facilitate the design of more pedestrian-friendly environments and the development of diverse approaches that utilize citizens for monitoring the built environment.


Entropy ◽  
2020 ◽  
Vol 22 (12) ◽  
pp. 1417
Author(s):  
Yamila M. Omar ◽  
Peter Plapper

Information entropy metrics have been applied to a wide range of problems that were abstracted as complex networks. This growing body of research is scattered in multiple disciplines, which makes it difficult to identify available metrics and understand the context in which they are applicable. In this work, a narrative literature review of information entropy metrics for complex networks is conducted following the PRISMA guidelines. Existing entropy metrics are classified according to three different criteria: whether the metric provides a property of the graph or a graph component (such as the nodes), the chosen probability distribution, and the types of complex networks to which the metrics are applicable. Consequently, this work identifies the areas in need for further development aiming to guide future research efforts.


Author(s):  
Peter Gibbs ◽  
H. Harry Asada

This paper describes a technique that uses conductive fibers as part of a wearable sensor for continuous monitoring of joint movements. Conductive fibers are incorporated into flexible, skin-tight fabrics that are comfortable and acceptable for long-term wear in everyday settings. Continuous monitoring of single or multi-axis joint movement is therefore possible, even when not in the presence of a therapist. A brief overview of the sensor design is presented, including functional requirements and important design parameters. Misalignment errors that may be created every time the subject takes off and puts on the wearable sensor are accounted for by incorporating an array of fiber sensors around the joint and analyzing each sensor’s sensitivity to joint movement during use. This eliminates any need for re-calibration after an initial calibration.


2021 ◽  
Vol 39 (28_suppl) ◽  
pp. 174-174
Author(s):  
Elad Neeman ◽  
Ai Kubo ◽  
Elaine Kurtovich ◽  
Sara Aghaee ◽  
Maya Ramsey ◽  
...  

174 Background: Patient-reported outcomes and wearable sensor measures of physical function can predict important outcomes in oncology. However, mobile and wearable-sensor apps collect vast information from patients and caregivers; indiscriminate reporting may increase provider burden and reduce data reliance. This study aimed to assess medical oncologists’ current practices in utilizing such information, and their data delivery preferences. Methods: Cross-sectional survey delivered by email to all Kaiser Permanente Northern California medical oncologists, February-March 2021. Results: Thirty-eight oncologists (30% of 127) responded to the survey. Most agreed that to reduce adverse events (AEs) it is important for the oncologist to know about the following measures: 1) patient/caregiver-reported physical symptoms (92% responded either very important or essential); 2) patient/caregiver-reported physical function (87%); and 3) objective measures of gait/balance (55%) and physical activity (50%) obtained from wearable sensors. Similarly, most respondents strongly consider these data when making decisions related to treatment intent, dosage, or visit frequency. All respondents routinely rely on information from caregivers, and in case of a discrepancy, more rely on the caregiver’s report (45%) than the patient’s report (8%), and some seek additional objective information (26%). Most respondents indicated that they prefer to receive electronic information on physical function and symptoms only for “critical values” and/or to have the information accessible “as needed” in the electronic chart, but not actively delivered to them (Table). Conclusions: Oncologists believe that patient/caregiver reports of symptoms and physical function can predict AEs, and strongly rely on them in clinical decision making. The majority of respondents would like to have access to physical function/symptoms data from mobile/wearable apps, with more providers wishing to receive information prior to a visit and/or in case of “critical values”. These findings may inform future implementations of mobile/wearable technologies to track symptoms and function of cancer patients.[Table: see text]


ACS Sensors ◽  
2019 ◽  
Vol 4 (11) ◽  
pp. 2945-2951 ◽  
Author(s):  
Daniela Maier ◽  
Elmar Laubender ◽  
Abhiraj Basavanna ◽  
Stefan Schumann ◽  
Firat Güder ◽  
...  

Entropy ◽  
2019 ◽  
Vol 21 (7) ◽  
pp. 630
Author(s):  
Diego Fasoli ◽  
Stefano Panzeri

In this paper, we study the statistical properties of the stationary firing-rate states of a neural network model with quenched disorder. The model has arbitrary size, discrete-time evolution equations and binary firing rates, while the topology and the strength of the synaptic connections are randomly generated from known, generally arbitrary, probability distributions. We derived semi-analytical expressions of the occurrence probability of the stationary states and the mean multistability diagram of the model, in terms of the distribution of the synaptic connections and of the external stimuli to the network. Our calculations rely on the probability distribution of the bifurcation points of the stationary states with respect to the external stimuli, calculated in terms of the permanent of special matrices using extreme value theory. While our semi-analytical expressions are exact for any size of the network and for any distribution of the synaptic connections, we focus our study on networks made of several populations, that we term “statistically homogeneous” to indicate that the probability distribution of their connections depends only on the pre- and post-synaptic population indexes, and not on the individual synaptic pair indexes. In this specific case, we calculated analytically the permanent, obtaining a compact formula that outperforms of several orders of magnitude the Balasubramanian-Bax-Franklin-Glynn algorithm. To conclude, by applying the Fisher-Tippett-Gnedenko theorem, we derived asymptotic expressions of the stationary-state statistics of multi-population networks in the large-network-size limit, in terms of the Gumbel (double exponential) distribution. We also provide a Python implementation of our formulas and some examples of the results generated by the code.


2018 ◽  
Vol 18 (2) ◽  
pp. 131-148
Author(s):  
Maria Hastuti ◽  
Martinis Yamin ◽  
Lukman Hakim

This study aims to examine the management of the Principal towards the school's income and expenditure budget (APBS) at Public High School or SMAN 10 East Tanjung Jabung, Jambi. The research was motivated by 1) APBS planning carried out by the Principal was only formulated by school managerial decision makers, was not discussed openly with all existing human resources, 2) there was still limited training by the Principal regarding the preparation of the APBS, 3) Principals had difficulty adjusting the APBS plan with needs, and 4) the assessment of the implementation of the APBS is not effective. This research uses qualitative methods that are based on the philosophy of postpositivism. Data is obtained through participation observation, interviews, and documentation. Based on the research,  it is known that the sources and budget allocations are still limited. there are still problems with the process, namely: a) Still difficult for budget users to specify budget requirements, b) The ability of administrative personnel to manage BOS is limited, c) school budget allocation as a source of school development is still not in accordance with the real needs of schools and d) Limitations of school principals carry out continuous monitoring. Planning activities are still not detailed, the implementation has been carried out in accordance with the planning, and the APBS evaluation has been carried out effectively.


2005 ◽  
Vol 14 (04) ◽  
pp. 653-661 ◽  
Author(s):  
K. CH. CHATZISAVVAS ◽  
C. P. PANOS

Three measures of the information content of a probability distribution are briefly reviewed. They are applied to fractional occupation probabilities in light nuclei, taking into account short-range correlations. The effect of short-range correlations is to increase the information entropy (or disorder) of nuclei, comparing with the independent particle model. It is also indicated that the information entropy can serve as a sensitive index of order and short-range correlations in nuclei. It is concluded that increasing Z, the information entropy increases, i.e. the disorder of the nucleus increases for all measures of information considered in the present work.


Sign in / Sign up

Export Citation Format

Share Document