Statistical Analysis of Index Values Extracted from Outdoor Agricultural Workers Motion Data

Kawakura, Shinji; Shibasaki, Ryosuke

doi:10.12720/joaat.1.1.69-74

Cited by 4 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang and Yin recognized human activities from wearable sensors using deep CNNs [17], similar to Hassan, et al [18]. Kawakura, and Shibasaki built integrated wearable sensing and agri-technical teaching systems, using three-axis acceleration sensors and angular velocity sensors, and Blockchain Corda-based IoT-Oriented Information-Sharing System for Agricultural Worker Physical Movement Data with Multiple Sensor Unit Shinji Kawakura and Ryosuke Shibasaki presented their statistics [19][20].…”

Section: Introductionmentioning

confidence: 88%

See 1 more Smart Citation

Blockchain Corda-based IoT-Oriented Information-Sharing System for Agricultural Worker Physical Movement Data with Multiple Sensor Unit

Kawakura

Shibasaki

2019

EJFOOD

View full text Add to dashboard Cite

In this study, we attempted to develop and implement a blockchain Corda-based record sharing system for traditional agricultural (agri-) researchers, workers, and their managers. Corda differs from other domain and practical blockchain techniques (e.g., Bitcoin, Ethereum) with respect to its main aims and structural features. Corda-based network systems can transmit and share basic data concerning ledgers at banks or other financial societies and can be handled on common web browsers (e.g., Google Chrome or Microsoft Internet Explorer). This study consists of three phases: (1) designing and confirming the validity of the entire system, (2) constructing and tuning various minor system settings (e.g., programs or networking specifications), and (3) conducting experiments in indoor settings using hoe acceleration data obtained from previous research projects. The integrated system performed with an acceptable level of accuracy. However, it was extremely difficult to quantitatively present the accuracy data. We were unable to concretely show the success and error rates for the data transmitting and receiving, nor the examination operation time. We thus present the specific error content. Overall, the main error trends were (1) errors concerning the rather small transaction time-delay, (2) mistakes concerning the transaction data in the system, and (3) broken transaction data in the system. In particular, we could determine the transaction time delay according to the JavaScript operations and features by observing. We present experimental ranges for these time delays and other error types. Noting concerns concerning previous trials, we suggest practical applications of the proposed system. In short, we believe that our results are novel achievements in the fusion of agricultural informatics, statistics, and human dynamics. We believe that combining this data and other kinds of timeline data with blockchain-based technology and multiple sensors will improve not only agri-business and management, but also agri-skill and security.

show abstract

Section: Introductionmentioning

confidence: 88%

“…Several studies have collected and analyzed diverse human or robot physical data [14][15][16][17][18][19][20]. Zhao, et al executed and presented a model targeting agri-robotics based on an acceleration sensor [14].…”

Section: Introductionmentioning

confidence: 99%

Blockchain Corda-based IoT-Oriented Information-Sharing System for Agricultural Worker Physical Movement Data with Multiple Sensor Unit

Kawakura

Shibasaki

2019

EJFOOD

View full text Add to dashboard Cite

show abstract

“…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

“…The target subjects were agri-workers with 1-5 years' experience ( 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 medium-sized outdoor farms [1]- [3].…”

Section: A Subject and Targetmentioning

confidence: 99%

“…Existing quantum deep learning-based analysis methods in the field of agriculture have focused on targets such as harvests, weeds, forests, and farmers [1]- [3]. However, these studies are insufficient, particularly for the analysis of data related to traditional Japanese workers.…”

Section: Introductionmentioning

confidence: 99%

Quantum Neural Network-Based Deep Learning System to Classify Physical Timeline Acceleration Data of Agricultural Workers

Kawakura

Shibasaki

2020

EJFOOD

Self Cite

View full text Add to dashboard Cite

In this study, we extract agricultural (agri-) workers’ physical acceleration timeline data and execute quantum neural network-based deep learning for data classification. Although various approaches have been implemented globally for indoor and outdoor agri-working sites, there is still scope for improvement. Therefore, in this study, we adapt these approaches mainly for automated, high-tech agri-sites and apply the quantum convolutional neural network (QCNN) deep learning-based method to qualitatively demonstrate the classification of physical workers’ timeline datasets. For our dataset, our subjects were six experienced and six completely inexperienced male agri-manual workers. The target task was to cultivate a farmland using a simple traditional Japanese hoe in a semi-crouching position. We captured the subjects’ acceleration data using an integrated multi-sensor module mounted on a wooden lilt 150 mm from the gripping position of the dominant hand. We developed and used Python (ver. 3.9) and recent distributed libraries for quantum computation and distributed concerned libraries. For data classification, we successively executed three patterns using QCNN, a category of quantum deep learning (QDL)-based deep learning, and evaluated the systems by obtaining loss, validation accuracy, and final epochs’ elapsed time data. These methods of analyzing digital data are expected to find practical applications and provide key suggestions for improving daily task efficiency.

show abstract

Statistical Analysis of Index Values Extracted from Outdoor Agricultural Workers Motion Data

Cited by 4 publications

References 5 publications

Blockchain Corda-based IoT-Oriented Information-Sharing System for Agricultural Worker Physical Movement Data with Multiple Sensor Unit

Blockchain Corda-based IoT-Oriented Information-Sharing System for Agricultural Worker Physical Movement Data with Multiple Sensor Unit

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

Quantum Neural Network-Based Deep Learning System to Classify Physical Timeline Acceleration Data of Agricultural Workers

Contact Info

Product

Resources

About