Papers and Publications

Find here all the results achieved during the research and development activities held in the SUNSpACe project

TITLE

TYPE

NAME OF MEDIUM

DATE

ABSTRACT

AUTHORS

KEYWORDS

Journal Paper

Applied Sciences. Vol 11,  no.  24(2021): p.11820

13/12/21

Water, an essential resource for crop production, is becoming increasingly scarce, while cropland continues to expand due to the world’s population growth. Proper irrigation scheduling has been shown to help farmers improve crop yield and quality, resulting in more sustainable water consumption. Soil Moisture (SM), which indicates the amount of water in the soil, is one of the most important crop irrigation parameters. In terms of water usage optimization and crop yield, estimating future soil moisture (forecasting) is an essentially valuable task for crop irrigation. As a result, farmers can base crop irrigation decisions on this parameter. Sensors can be used to estimate this value in real time, which may assist farmers in deciding whether or not to irrigate. The soil moisture value provided by the sensors, on the other hand, is instantaneous and cannot be used to directly compute irrigation parameters such as the best timing or the required water quantity to irrigate. The soil moisture value can, in fact, vary greatly depending on factors such as humidity, weather, and time. Using machine learning methods, these parameters can be used to predict soil moisture levels in the near future. This paper proposes a new Long-Short Term Memory (LSTM)-based model to forecast soil moisture values in the future based on parameters collected from various sensors as a potential solution. To train and validate this model, a real-world dataset containing a set of parameters related to weather forecasting, soil moisture, and other related parameters was collected using smart sensors installed in a greenhouse in Chiang Mai province, Thailand. Preliminary results show that our LSTM-based model performs well in predicting soil moisture with a 0.72% RMSE error and a 0.52% cross-validation error (LSTM), and our Bi-LSTM model with a 0.76% RMSE error and a 0.57% cross-validation error. In the future, we aim to test and validate this model on other similar datasets.

Paweena Suebsombut,

College of Arts, Media and Techology, Chiang Mai University, Chiang Mai, Thailand

 

Aicha Sekhari, Decision and Information Sciences for Production Systems, University Lumiere Lyon 2


Pradorn Sureephong, College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand


Abdelaziz Bouras

Soil Moisture, Smart Irrigation, Machine Learning, Deep Learning, LSTM, Bidirectional LSTM

Journal Paper

The Journal of Modern Project Management, July 2021

5/10/21

Crop lifecycle management is important for cropcare and maintenance throughout its life. The existing recommendation and expert systems do not provide advice for the entire crop lifecycle. However, each stage of the crop’s lifecycle necessitates a different set of recommendations.As a result, this paper proposed a recommendation system based on sensor data and rule-based extraction from expert people to provide crop management advice throughout its lifecycle. The proposed system ‘s rules are built around IF-THEN situations.The proposed system will analyze the data by searching for relationships between input data and rule-based using a php script to define the best recommendation for farmers. This proposed system was put into action in a greenhouse dome in Chiang Mai, Thailand. Farmers were overwhelmingly pleased with it, giving it a 96%satisfaction rating.

Paweena Suebsombut,

College of Arts, Media and Techology, Chiang Mai University, Chiang Mai, Thailand

 

Aicha Sekhari, Decision and Information Sciences for Production Systems, University Lumiere Lyon 2


Pradorn Sureephong, College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand


Abdelaziz Bouras

Crop lifecycle, Crop lifecycle management 

Conference

Paper

2022Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering

(ECTI DAMT & NCON)

4/03/22

A chatbot is a software developed to help reply to text or voice conversations automatically and quickly in real time. In the agriculture sector, the existing smart Agriculture systems just use data from sensing and internet of things (IoT) technologies that exclude crop cultivation k knowledge to support decision-making by farmers. To enhance this, the chatbot application can be an assistant to farmers to provide crop cultivation knowledge. Consequently, we propose the LINE chatbot application as an information and knowledge representation providing crop cultivation recommendations to farmers. It works with smart agriculture and recommendation systems. Our proposed LINE chatbot application consists of five main functions (start/stop menu, main page, drip irrigation page, mist irrigation page, and monitor page ). Framers will receive information for data monitoring to support their decision-making. Moreover, they can control the irrigation system via the LINE chatbot. Furthermore, farmers can ask questions relevant to the crop environment via a chat box. After implementing our proposed chatbot, farmers are very satisfied with the application, scoring a 96% satisfaction score. However, in terms of asking Questions via chat box, this LINE chatbot application is a rule-based bot or script bot. Framers have to type in the correct keywords as prescribed, otherwise they won’t get a response from the chatbots. In the future, we will enhance the asking function of our LINE chatbot to be an intelligent bot.

Paweena Suebsombut,

College of Arts, Media and Techology, Chiang Mai University, Chiang Mai, Thailand

 

Aicha Sekhari, Decision and Information Sciences for Production Systems, University Lumiere Lyon 2

 

Pradorn Sureephong

College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand

 

Suepphong Chernbumroong, College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand

 

Abdelaziz Bouras

Chatbot Application, Crop Cultivation, Smart Agriculture, Knowledge
Information Representation

Conference

Paper

2022Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering

(ECTI DAMT & NCON)

4/03/22

Farmers can now use IoT to improve farm efficiency and productivity by using sensors for farm monitoring to enhance decision-making in areas such as fertilization, irrigation, climate forecast, and harvesting information. Local farmers in Chiang Mai, Thailand, on the other hand, continue to lack knowledge and experience with smart farm technology. As a result , the ‘SUNSpACe’ project, funded by the European Union’s Erasmus+ Program, was launched to launch a training course which improve the knowledge and performance of  Thai farmers. To assess the effect iveness of the t raining, The Kirkpatrick model was used  in this study. Eight local farmers took part in the training, which was divided into two sections: mobile learning and smart farm laboratory. During the training  activities,  different   levels of the Kirkpatrick model were conducted and tested: reaction (satisfaction test), learning  (knowledge test ), and behavior (performance test). The overall result demonstrated the participants positive reaction to the outcome. The paper also discusses the limitations and suggestions  for training activities.

Paweena Suebsombut,

College of Arts, Media and Techology, Chiang Mai University, Chiang Mai, Thailand

 

Aicha Sekhari, Decision and Information Sciences for Production Systems, University Lumiere Lyon 2

 

Pradorn Sureephong

College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand

 

Suepphong Chernbumroong, College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand

Smart Farmers, Kirkpatrick Model, Training Evaluation

Conference

Paper

2020 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecom-munications Engineering (ECTI DAMT & NCON)

11/05/20

Smart  agriculture  is  a  concept  of  management of  modern  farming  using  smart/digital  techniques  to monitor,  to optimize, and  to control processes  of  agricultural production.  To  manage  farm  presently,  the  literacy  in smart  agricultural  technologies  is  significant  so  that farmers  need  to  improve  themselves  to  adopt  smart technologies  for  farming.  However,  each  farmer  has  the difference  skills  and  experience  into  adoption  of  smart agriculture technologies. Therefore, the aims of this paper is to survey  smart  agriculture  literacy  of  farmers’  skills  and experience,  specific  in  Chiang  Mai  and  Khon  Kaen province,  Thailand.  The  questionnaire  was constructed based  on  smart farmer’s properties. The results of this paper reveal the comparison of  smart agriculture  literacy of  farmers in  Chiang  Mai  and  Khon  Kaen  province,  Thailand,  by analyzing the survey results. According to the survey analysis results,  farmers  in  Chiang  Mai  and  Khon  Kaen  province  are totally  different  of  smart  agriculture  literacy  due  to  their farming experiences, training experiences, age, background, etc. 

Paweena Suebsombut,

College of Arts, Media and Techology, Chiang Mai University, Chiang Mai, Thailand

 

Aicha Sekhari, Decision and Information Sciences for Production Systems, University Lumiere Lyon 2

 

Pradorn Sureephong,

College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand

 

Suepphong Chernbumroong, College of Arts, Media and Techology, Chiang Mai University Chiang Mai, Thailand

 

Pensri Jaroenwanit , Faculty of Business Administration and Accountancy, Khon Kaen University

 

Pongsutti Phuensane

Faculty of Business Administration and Accountancy, Khon Kaen University

Survey, Smart Farming, Smart Farmers, Smart Agriculture

Conference

Paper

2020 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on
Electrical, Electronics, Computer and Telecom-

munications Engineering (ECTI DAMT & NCON)

11/03/20

Smart farming is the future of agriculture that represents the use of modern technologies with the help of Internet of Things (IoT), sensors, Big Data, robotics, and Unmanned Aerial Vehicles (UAVs/drones) etc into agriculture, leading to Agriculture 4.0. Smart farming is a farming management concept, which engenders, garner and analysis agricultural big data to ameliorate the productivity and sustainability in agriculture. Nowadays, the farmers need professional skills with technological knowledge for powering smart farming. So, that farmers can monitor and control several measuring parameters within a field and adopting the decision accordingly e.g. use of pesticides and fertilizers. In this paper, we have proposed a cluster-based knowledge transfer approach for building up smart farming. The objective is to design and develop learning framework for transforming traditional farmers into intelligent farmers, known as “iFarmer”. This study also illustrates the resent literatures of smart farming and teaching and learning lifecycle for producing organic fruits and vegetables employing smart information and communications technology (ICT).

Dewan Md. Farid

 

Aicha Sekhari, Decision and Information Sciences for Production Systems, University Lumiere Lyon 2

 

Ouzrout Yacine

Agriculture 4.0, Intelligent Farmer, Knowledge Transfer, Smart Farming

Conference

Paper

2020 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecom-munications Engineering (ECTI DAMT & NCON)

11/05/21

Smart agriculture is just beginning to emerge and there are only a few instances of the use of smart technologies in Bhutan. This study aimed to understand the farming activity, their ability and experience with smart farming for designing appropriate learning tools for farmers to enhance agricultural production. Fifty respondents (34 females and 16 male) from Barp gewog (block), Punakha District were randomly selected and interviewed using a semi-structured questionnaire. The findings showed that the majority (56 %) used martphones, among them 52 % used for communication and 32 % for taking photos. Radio and TV were the sources of information on the weather forecast (86 %), and agricultural-related information (70 %). More than 80% of respondents fall below the basic level in all aspects of digital literacy. For the management of crops, 72 % applied both chemical and organic fertilizers, 26 % used organic fertilizers and 2 % used chemical fertilizers to maintain soil fertility. Many adopted mechanical ways (85.7%) to manage pest and disease and manual weeding (76%) to manage weeds in the field. The Majority (86%) of the respondents directly sold produce to consumers in the market and no webpage were used
to sell their agricultural products. The majority (92 %) did not have a business model to sale agricultural product and none used software or technology to plan for business. Besides, none of the respondents had adopted smart farming technology nor had any experience with smart farming. In conclusion, farmers have limited knowledge on the use of smart technology for agriculture.

Ugyen Yangchen

 

Phub Dorji

 

Sylvain Touchard

 

Paweena 

Suebsombut

 

Suepphong 

Chernbumroong

 

Tashi Lhamo

 

Pradorn Sureephong

Digital literacy, Smart Agriculture, Smart Technology,
Smart Farmers

An Adaptive Learning Approach to Train Smart Farmers in Thailand, Bhutan and Nepal

Conference

Paper

2020 the 2nd International Conference on Modern Educational Technology (ICMET 2020)

18/06/20

In this paper, we describe past approaches used to teach Farmers in Asia, and propose an adaptive learning approach appropriate to teach Asian farmers the basics of Digital Agriculture (overview, components, data processing and decision models), Smart Farming (objectives, cultivation farming, livestock farming, smart monitoring, smart controlling), Standardization (food safety and standards/norms) and Agro business (business modelling, sales and marketing).

Aurelie Charles,

DISP Laboratory, University of Lyon, Bron, France

 

Claudine Gay,

Triangle Laboratory, University of Lyon, Bron, France

 

Paweena Suebsombut,

Mae Fah Luang University Chiang Rai, Thailand

 

Keshar Prasain, Kantipur Engineering College Dhapakhel, Lalitpur, Nepal

Smart Farming, Learning approach

Conference

Paper

14th International conference on software, knowledge, information management and applications (SKIMA)

2 to 4

Dec 22

This research is a conceptual paper, aims to investigate the determinants of intention to continue using Smart farming and the resulting sustainability of smart farming among farmers who are on smart agriculture. The constructs of decomposed expectancy disconfirmation theory (DEDT) are evaluated from the perspective of smart farmers in relation to smart farming success variables, perceived usefulness, intention to continue using smart farming and sustainability of smart farming. The expected outcome of the study is the development of a model of factors affecting continuance intention on smart

farming and sustainability. 

Pensri Jaroenwanit
Faculty of Business Administration and
Accountancy, Khon Kaen University
Khon Kaen, Thailand

 

Watis Leelapatra
Faculty of Engineering,
Khon Kaen University
Khon Kaen, Thailand

 

Zoltán Szabó
Department of Information Systems,
Corvinus University of Budapest
Budapest, Hungary

Smart farming, Continuance intention, Sustainability

Conference

Paper

14th International conference on software, knowledge, information management and applications (SKIMA)

2 to 4

Dec 22

This paper discusses different drying methods for herbs and vegetables and demonstrates the benefits of using a dehydrator over other methods. Not all temperatures are ideal for drying herbs; there are various  precautions and specific temperatures to obtain high-quality herbs. It also discusses thesmart dehydrator, which is built with a PID control system  and can be controlled by an IOT platform. Arduino Uno is responsible for the PID control system. This dehydrator is a smart dehydrator. Various herbs were dried as a sample and yielded positive results

Piyush Tiwari
KIT’s College of Engineering,

Kolhapur India

 

Amarsihn Desai
KIT’s College of Engineering
Kolhapur India

 

Mahesh Chavan
KIT’s College of Engineering.
Kolhapur, India

 

Pradorn Sureephong
College of Arts, Media and Technology, Chiang
Mai University

 

Sylvain Touchard
Decision and Information Systems for Production
systems lab-IUT Lumière – University of Lyon 2,
Lyon, France

Survey, Smart Farming, Smart Farmers, Smart Agriculture

Conference

Presentation

2021 International Workshop on Industry 4.0 and Intelligent Manufacturing 9/9/2021. Dongguan University of Technology

(DGUT), China

9/9/21

Smart farming has several potential benefits by promoting community farming, improving safety control and fraud prevention, providing cost and waste reduction opportunities, improving operational efficiency, ensuring transparency and traceability. Smart technologies in the agriculture can be a major source of competitive advantages, they increase productivity, facilitate better decision-making or more efficient exploitation of operations, resources, smart technologies can also underpin new business models. The technologies that underpin Smart Farming are still in early development, but there are many promising opportunities. Typical applications are: irrigation automation, temperature, pH, humidity, carbon dioxide level control, soil nutrient replenishment (fertilizer) automation, soil moisture detection, and crop monitoring, estimation. Although the application of Industry 4.0 technologies in the agriculture is very promising, and there are many successful application cases, widespread adoption will take time, as it requires significant change in practices and mindset, modernisation of the equipment and supporting infrastructures. The presentaton gives an overview of an EU funded project SUNSpACe, that provides an Education and Training System to help Farmers understand the use and usefulness of the new technologies. SUNSpACe offers an appropriate adaptive learning approach, tools and ready to use learning materials to be implemented in Smartfarm labs.

András Gábor and Zoltán Szabó


Department of Information Systems,
Corvinus University of Budapest
Budapest, Hungary
andras.gabor@uni-corvinus.hu, zoltan.szabo@uni-corvinus.hu

Survey, Smart Farming, Smart Farmers, Smart Agriculture

Conference

Paper

14th International conference on software, knowledge, information management and applications (SKIMA)

2 to 4

Dec 22

In the process of planting, weeds will inevitably grow in the farmland, and compete with crops for water, light and space, which obviously affect our normal agriculture. If weeds are not effectively controlled, crops yield will be seriously compromised. Nowadays, weeding methods heavily rely on labor and herbicide. However, manual weeding is inefficient, costly, time consuming and cannot remove weeds effectively. The purpose of this paper is to propose a weeding robot. Our research focus on how to use dual cameras to accurately detect weeds. The convolutional neural networks (CNNs), deep learning, dual cameras machine vision and mechanical design will be discussed in this paper. Experimental results show that dual cameras robot based on a new lightweight platform we proposed achieve a high accuracy compared to single camera method. As a result, our method achieves 98.12% precision, 83.47% recall and 89.91% mAP that is 4.06% higher than using only a single top-view camera. GF-YOLO, a lightweight platform we proposed also outperform other state-of-the-art algorithms in embedded system.

MingYuan Wang
Graduate Student, Department of Computer Engineering
Faculty of Engineering, Khon Kaen University
Khon Kaen, Thailand


Watis Leelapatra
Department of Computer Engineering
Faculty of Engineering, Khon Kaen University
Khon Kaen, Thailand

machine vision, weeding robot, dual cameras, deep learning, smart farming

Risk management in the adoption of smart farming technologies by rural farmers

Journal

Paper

Uncertain Supply Chain Management, An international journal

2023

COMING SOON

Pongsutti Phuensane
Faculty of Business Administration and Accountancy, Khon Kaen University

 

Claudine Gay,

Triangle Laboratory, University of Lyon, Bron, France

 

Aicha Sekhari

Decision and Information Sciences for Production Systems, University Lumiere Lyon 2

COMING SOON