Smart Farming

Under Construction

In HCC-Laboratory, we currently conducting various kinds of research related to smart farming. Here are the sub-topics of research at HCC Lab

Smart Farming and Artificial Intelligence
The goal in proposing this research is to develop smart-farming and provide an application that can help farmers increase cocoa production by developing methods to attract and promote pollinators.


Research output:
- Syafruddin, Willa Ariela, Rio Mukhtarom Paweroi, and Mario Köppen. "Behavior Selection Metaheuristic Search Algorithm for the Pollination Optimization: A Simulation Case of Cocoa Flowers." Algorithms 14, no. 8 (2021): 230.
- Mantau, Aprinaldi Jasa, Irawan Widi Widayat, and Mario Köppen. "A Genetic Algorithm for Parallel Unmanned Aerial Vehicle Scheduling: A Cost Minimization Approach." In International Conference on Intelligent Networking and Collaborative Systems, pp. 125-135. Springer, Cham, 2021.

Smart Farming and BlockChain and Networking
Thecertaintyoffoodprovenanceontheagricultureecosystembrings one of the most popular research topics to smart farming. The global epidemic enforces consumers to be warned of the originality of food supply. Various technol- ogy unification is included to address this problem. Heterogeneous IoT sensors for sensing agricultural or plantation land provide system automation and monitoring for certain commodities. Sensor data and captured images of surveillance cameras are the results of IoT devices sensing capability. However, the originality of the data being stored is questioned; even worse, the data records are deleted. Such as problems occur due to several things: network congestion, device reliability, stor- age media, and operator. One of the findings proposed in this research is storing sensing results from each sensor and camera surveillance to a global database that is decentralized, immutable, and synchronized, known as the blockchain. All the parties involved in the smart farming system, such as farmers, food suppliers, and customers, are connected to a global blockchain network. Multi-Image Encryption (MIE) yields to secure the authenticity of captured images from multiple cameras. A specific MIE algorithm will compile and randomized the captured image from cameras to produce an encrypted image stored in the blockchain database with a unique identifier. This study provides a simulated model of blockchain technology that can be implemented in a smart farming environment using Ganache as the test net. In the smart contract, every entity connected to the blockchain network appears as a node account that is digitally assigned based on each role. Therefore, the transaction was successfully done from one node to the others. This research is the initial stages of implementing a smart farming system into the unification of various technology in the development of sustainable agriculture.


Research output:
- Widi Widayat, Irawan, and Mario Köppen. "Blockchain Simulation Environment on Multi-image Encryption for Smart Farming Application." In International Conference on Intelligent Networking and Collaborative Systems, pp. 316-326. Springer, Cham, 2021.
- Sirimorok, Nurdiansyah, Mansur As, Kaori Yoshida, and Mario Köppen. "Smart Watering System Based on Framework of Low-Bandwidth Distributed Applications (LBDA) in Cloud Computing." In International Conference on Intelligent Networking and Collaborative Systems, pp. 447-459. Springer, Cham, 2020.



Smart Farming and Image Processing


Research output:
- Parewai, Ismail, Mansur As, Tsunenori Mine, and Mario Koeppen. "Identification and Classification of Sashimi Food Using Multispectral Technology." In Proceedings of the 2020 2nd Asia Pacific Information Technology Conference, pp. 66-72. 2020.

Smart Farming and Internet of Things
Feature Extraction for Cocoa Bean Digital Image Classification Prediction for Smart Farming Application: This study demonstrated a methodology for textural feature analysis on digital images of cocoa beans. The co-occurrence matrix features of the gray level co-occurrence matrix (GLCM) were compared with the convolutional neural network (CNN) method for the feature extraction method. In addition, we applied several classifiers for conclusive assessment and classification to obtain an accuracy performance analysis.

Design and Implementation of LoRa Based IoT Scheme for Indonesian Rural Area: This study proposes the IoT scheme for long-range communication based on Long Range (LoRa) modules applied to smart agriculture. The scheme utilizes the low power modules and long-distance communication for monitoring temperature, humidity, soil moisture, and pH soil. Our IoT design has successfully been applied to agriculture areas which have unstable network connections. The design is analyzed to obtain the maximum coverage using different spreading factors and bandwidths.

(2018-2019) : IoT in rural, outdoor, remote and farming environments (Internet of Things, Monitoring, Sensors, Wireless Service) Collaboration Program by and between Kyushu Institute of Technology (Kyutech) and National Taiwan University of Science and Technology (Taiwan-Tech)

(2019-2020) : IoT in rural, outdoor, remote and farming environments (Internet of Things, Monitoring, Sensors, Wireless Service) Collaboration Program by and between Kyushu Institute of Technology (Kyutech) and National Taiwan University of Science and Technology (Taiwan-Tech)



Research output:
- Prakosa, Setya Widyawan, Muhamad Faisal, Yudhi Adhitya, Jenq-Shiou Leu, Mario Köppen, and Cries Avian. "Design and Implementation of LoRa Based IoT Scheme for Indonesian Rural Area." Electronics 10, no. 1 (2021): 77.
- Adhitya, Yudhi, Setya Widyawan Prakosa, Mario Köppen, and Jenq-Shiou Leu. "Feature Extraction for Cocoa Bean Digital Image Classification Prediction for Smart Farming Application." Agronomy 10, no. 11 (2020): 1642.

LAB PROFILE

MEMBER

PROJECTS

PHOTO & VIDEO

VISIT US

LINK

login

Blix theme adapted by David Gilbert, powered by PmWiki