Timeline Effects of Vocal Instructions from Computer Programs on Agricultural Technical Teaching

Kawakura, Shinji; Shibasaki, Ryosuke

doi:10.12720/joaat.1.2.104-112

Cited by 9 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior to the data collection, we consulted agri-managers and workers to mitigate the difficulties in handling dozens of samples in farmlands. Following consultations with Japanese farmers, we focused on agri-workers using a traditional Japanese hoe, which is the most familiar agri-tool in traditional Japanese small-to middle-sized outdoor farms after consultation with real farmers [12], [13]. First, we accumulated four categories of datasets ( Fig.…”

Section: Subject and Targetmentioning

confidence: 99%

Deep Learning Based System to Extract Agricultural Workers’ Physical Timeline Data for Acceleration and Angular Velocity

Kawakura¹,

Shibasaki²

2020

IJBBB

Self Cite

View full text Add to dashboard Cite

Several physical characteristics of workers can be extracted from physical timeline data to understand acceleration and angular velocity. Although various approaches have been implemented globally for indoor and outdoor agricultural (agri-) working sites, there is room for improvement. In this study, we aim to adapt these approaches particularly for real agri-directors, leaders and managers to improve the quality of tasks and their security levels. Thus, we apply a deep learning-based method and qualitatively demonstrate the classification of physical timeline datasets. To create our dataset, our subjects were six experienced agri-manual workers and six completely inexperienced men. The targeted task was cultivating the semi-crunching position using a simple, Japanese-style hoe. We captured the subjects' acceleration and angular velocity data from an integrated multi-sensor module mounted on a wood lilt 15 cm from the gripping position of the dominant hand. We used Python code and recent distributed libraries for computation. For data classification, we successively executed a Recurrent Neural Network (RNN), which we evaluated using wavelet analyses such as the Fast Fourier Transform (FFT). These methods of analyzing digital data could be of practical use for providing key suggestions to improve daily tasks.

show abstract

Section: Subject and Targetmentioning

confidence: 99%

Deep Learning Based System to Extract Agricultural Workers’ Physical Timeline Data for Acceleration and Angular Velocity

Kawakura¹,

Shibasaki²

2020

IJBBB

Self Cite

View full text Add to dashboard Cite

show abstract

“…We assumed that these experimental settings were practical for use by general agricultural workers, directors, and managers to obtain time-series of visual data for diverse analyses of outdoor experiments with reference to past studies [5], [10], [12], [14], [15].…”

Section: System and Theory Of Visual Data Analysismentioning

confidence: 99%

“…Many researchers in the field of agricultural informatics have been proposing various methods for solving these problems. There are existing methods that have successfully characterized the motion of agricultural workers and their machinery, which have gradually led to an increased crop yield [1]- [5].…”

Section: Introductionmentioning

confidence: 99%

3D Wavelet Analysis of Movement Acceleration Data in Agricultural Workers Using a Hoe

Kawakura¹,

Shibasaki²

2018

JOAAT

Self Cite

View full text Add to dashboard Cite

We have been developing diverse promising and radical analysis systems to address various agricultural challenges in our sequential studies. One purpose of this prospective research was to verify and demonstrate the accuracy and utility of our kinematic visual analysis system, which was based on the recent Scilab series platform for Windows 10 OS, and to present qualitative and quantitative differences of unique parameters between groups of experienced and inexperienced agricultural workers. We used the latest Scilab PC program libraries and packages to investigate, select, and execute both 2D and 3D timeline wavelet analyses, including SURF 3D expressions with accumulated fundamental data from our subjects. From these results, we were able to show various charts and a range of differences between experienced and inexperienced subjects. Our target field was situated in a common outdoor farm in Japan, and the target work was common tilling (cultivating) using a general hoe, i.e., one of the most common movements worldwide. These visual methods of analyzing digital data could be of practical use in providing important indicators concerning the improvement of the users' working movements and habits in outdoor fields.  Index Terms-wavelet analysis, Scilab, SURF 3D expression, indicators for agricultural workers, time-line acceleration data

show abstract

“…We also accumulated timeline data from 18 points on the subject's body including 3D-coordinates (the amount of transfer in space), speed, posture (using quaternion values), acceleration, and angular velocity using Perception Neuron (PN); one motion capture system. We have been developing methods for the remote observation of physically challenged people in parallel with contact-type methods (e.g., wearable electronic systems [19], [20]) for many years. These visual methods of analyzing digital data from systems could be useful and provide promising indicators for not only improving users' movements but also revising nursing techniques.…”

Section: Introductionmentioning

confidence: 99%

Visual Data Analysis Methods Using OpenCV Programs to Evaluate Walking and Falling with a Japanese Walking Support System

Kawakura¹

2018

IJBBB

Self Cite

View full text Add to dashboard Cite

Abstract:In recent years, researchers and engineers have come together to develop diverse, applied, and practical sensing systems to solve the difficulties faced in the development of advanced support systems, technical teaching, and safety issues for physically challenged and elderly people. Following a sequence of studies developing promising systems that address a number of nursing challenges, the purpose of this prospective research was to develop effective systems and demonstrate their accuracy and utility for the aforementioned people. In this kinematic investigation, we develop a physical analysis system, which uses two video cameras to obtain visual data of physically challenged and elderly people from two directions (the subject's front and left). These systems use the OpenCV 2.4.9 package, including the library and header files, and programs originally written in Visual C++. This study examines the qualitative and quantitative characteristics and the unique parameters of (1) the main shaft (the principal axis of inertia) of the subject and the walking support system to highlight the differences between two frames using binary video data, and (2) coordinate values of characteristic points that are set automatically. Finally, we present the output values for the physical measurements obtained from various viewpoints. In future, these methods could be of practical use in providing alternative directions for developers and care managers to assess and treat users' conditions in both outdoor (e.g., playgrounds for the elderly) and indoor settings (e.g., hospitals).

show abstract

Timeline Effects of Vocal Instructions from Computer Programs on Agricultural Technical Teaching

Cited by 9 publications

References 0 publications

Deep Learning Based System to Extract Agricultural Workers’ Physical Timeline Data for Acceleration and Angular Velocity

Deep Learning Based System to Extract Agricultural Workers’ Physical Timeline Data for Acceleration and Angular Velocity

3D Wavelet Analysis of Movement Acceleration Data in Agricultural Workers Using a Hoe

Visual Data Analysis Methods Using OpenCV Programs to Evaluate Walking and Falling with a Japanese Walking Support System

Contact Info

Product

Resources

About