Life Sciences Commons^™

Application Of Advanced Algorithms And Statistical Techniques For Weed-Plant Discrimination, Saman Akbar Zadeh

Theses: Doctorates and Masters

Precision agriculture requires automated systems for weed detection as weeds compete with the crop for water, nutrients, and light. The purpose of this study is to investigate the use of machine learning methods to classify weeds/crops in agriculture. Statistical methods, support vector machines, convolutional neural networks (CNNs) are introduced, investigated and optimized as classifiers to provide high accuracy at high vehicular speed for weed detection.

Initially, Support Vector Machine (SVM) algorithms are developed for weed-crop discrimination and their accuracies are compared with a conventional data-aggregation method based on the evaluation of discrete Normalised Difference Vegetation Indices (NDVIs) at two different …

Local Binary Pattern Based Algorithms For The Discrimination And Detection Of Crops And Weeds With Similar Morphologies, Vi Nguyen Thanh Le

Theses: Doctorates and Masters

In cultivated agricultural fields, weeds are unwanted species that compete with the crop plants for nutrients, water, sunlight and soil, thus constraining their growth. Applying new real-time weed detection and spraying technologies to agriculture would enhance current farming practices, leading to higher crop yields and lower production costs. Various weed detection methods have been developed for Site-Specific Weed Management (SSWM) aimed at maximising the crop yield through efficient control of weeds. Blanket application of herbicide chemicals is currently the most popular weed eradication practice in weed management and weed invasion. However, the excessive use of herbicides has a detrimental impact …

Vegetable And Fruit Intake And Fracture-Related Hospitalisations: A Prospective Study Of Older Women, Lauren C. Blekkenhorst, Jonathan M. Hodgson, Joshua R. Lewis, Amanda Devine, Richard J. Woodman, Wai H. Lim, Germaine Wong, Kun Zhu, Catherine P. Bondonno, Natalie C. Ward, Richard L. Prince

Research outputs 2014 to 2021

The importance of vegetable and fruit intakes for the prevention of fracture in older women is not well understood. Few studies have explored vegetable and fruit intakes separately, or the associations of specific types of vegetables and fruits with fracture hospitalisations. The objective of this study was to examine the associations of vegetable and fruit intakes, separately, and specific types of vegetables and fruits with fracture-related hospitalisations in a prospective cohort of women aged ≥70 years. Vegetable and fruit intakes were assessed at baseline (1998) in 1468 women using a food frequency questionnaire. The incidence of fracture-related hospitalisations over 14.5 …

A Survey Of Image Processing Techniques For Agriculture, Lalit Saxena, Leisa Armstrong

Research outputs 2014 to 2021

Computer technologies have been shown to improve agricultural productivity in a number of ways. One technique which is emerging as a useful tool is image processing. This paper presents a short survey on using image processing techniques to assist researchers and farmers to improve agricultural practices. Image processing has been used to assist with precision agriculture practices, weed and herbicide technologies, monitoring plant growth and plant nutrition management. This paper highlights the future potential for image processing for different agricultural industry contexts.

Decision Support System Data For Farmer Decision Making, Pornchai Taechatanasat, Leisa Armstrong

Research outputs 2014 to 2021

The capacity of farmers and agricultural scientists to be able to make in-season decisions is dependent on accurate climate, soil and plant data. This paper will provide a review of the types of environmental and crop data that can be collected by sensors which can used for decision support systems (DSS) or be further interrogated for real time data mining and analysis. This paper also presents a review of the data requirements for agricultural decision making by firstly reviewing decision support frameworks and agricultural DSSs, data acquisition, sensors for data acquisition and examples of data incorporation for agricultural DSSs.

Role Of Icts In Improving Drought Scenario Management In India, Shubhangi S. Wankhede, Niketa Gandhi, Leisa Armstrong

Research outputs 2014 to 2021

Drought is a natural phenomenon that affects social, economic and environmental sectors. It is caused due to low or no rainfall in the specific region and for some duration of time. Reduced soil moisture and ground water level are the other causes for drought. Based on its intensity, drought has impacts on various sectors like agriculture, transportation, forest fire, environment and many more. Agriculture is the major sector being affected by drought resulting in low crop production and having great detriment to economy of the country. In this paper, an attempt is made to study the different causes and effects …

Development Of An Optical Sensor For Real-Time Weed Detection Using Laser Based Spectroscopy, Arie Jacobus Paap

Theses: Doctorates and Masters

The management of weeds in agriculture is a time consuming and expensive activity, including in Australia where the predominant strategy is blanket spraying of herbicides. This approach wastes herbicide by applying it in areas where there are no weeds. Discrimination of different plant species can be performed based on the spectral reflectance of the leaves. This thesis describes the development of a sensor for automatic spot spraying of weeds within crop rows. The sensor records the relative intensity of reflected light in three narrow wavebands using lasers as an illumination source.

A prototype weed sensor which had been previously developed …

Icts For Agricultural Extension: A Study In Ratnagiri District Of Maharashtra, India, Niketa Gandhi, Leisa Armstrong

Research outputs 2014 to 2021

This study describes an assessment of attitudes of farmers from the Lanja tehsil of Ratnagiri district of Maharashtra in order to understand the information seeking behavior and reasons for the farmers seeking this agricultural information through different sources. To meet the objective of the study, a structured questionnaire and interviews were conducted to gather information on number of aspects related to the use of Information and Communication Technologies (ICT) from 100 randomly selected framers. Additional semi- structured questionnaire and checklist was provided to the key stakeholders. The farmer based questionnaire sought demographic data, information requirement data and uses of ICT …

Mobile Applications For Indian Agriculture Sector: A Case Study, Pratik Shah, Niketa Gandhi, Leisa Armstrong

Research outputs 2014 to 2021

Government, private agencies and the general public are often interested in the decisions made by the Indian farmers as they have large influences beyond the farm boundary. Over many years, the process of adoption of new technologies and policies in the Indian agricultural sector has received considerable academic attention highlighting the role of many social, financial and other influences on their decision making. The Indian government and other development agencies promote income generating projects as a way of encouraging growth through increased agricultural production and the protection of the natural resource base. The impact of new technology to economic growth …

Application Of Cellular Neural Networks And Naive Bayes Classifier In Agriculture, Oluleye H. Babatunde, Leisa Armstrong, Jinsong Leng, Dean Diepeveen

Research outputs 2014 to 2021

This article describes the use of Cellular Neural Networks (a class of Ordinary Differential Equation (ODE)), Fourier Descriptors (FD) and NaiveBayes Classifier (NBC) for automatic identification of images of plant leaves. The novelty of this article is seen in the use of CNN for image segmentation and a combination FDs with NBC. The main advantage of the segmentation method is the computation speed compared with other edge operators such as canny, sobel, Laplacian of Gaussian (LoG). The results herein show the potential of the methods in this paper for examining different agricultural images and distinguishing between different crops and weeds …

A Network That Really Works - The Application Of Artificial Neural Networks To Improve Yield Predictions And Nitrogen Management In Western Australia, Jinsong Leng, Andreas Neuhaus, Leisa Armstrong

Research outputs 2014 to 2021

Yield predictions are notorious for being difficult due to many interdependent factors such as rainfall, soil properties, plant health, plant density etc. This study is based upon the author’s previously published work and extends its findings by further investigating the best mathematical solution to this dilemma. Artificial intelligence (AI) techniques have been applied to a large set of soil, plant, rainfall, and yield data from CSBP’s field research trial program. Here we further differentiate by investigate two ANN techniques, a genetic algorithm with back propagation neural networks (GA-BP-NN) and a particle swarm optimization with back propagation neural networks (PSO-BP-NN). Results …

An Artificial Neural Network For Predicting Crops Yield In Nepal, Tirtha Ranjeet, Leisa Armstrong

Research outputs 2014 to 2021

This paper examines the application of artificial neural networks (ANNs) for predicting crop yields for an agricultural region in Nepal. The neural network algorithm has become an effective data mining tool and the outcome produced by this algorithm is considered to be less error prone than other computer science techniques. The backpropagation algorithm which iteratively finds a suitable weight value is considered for computing the error derivative. Agricultural data was collected from thirteen years from paddy field cultivation in the Siraha district, an eastern region in Nepal, and used for this investigation of neural networks. Additionally, climatic parameters including rainfall, …

Integrating Soil And Plant Tissue Tests And Using An Artificial Intelligence Method For Data Modelling Is Likely To Improve Decisions For In-Season Nitrogen Management, Andreas Neuhaus, Leisa Armstrong, Jinsong Leng, Dean Diepeveen, Geoff Anderson

Research outputs 2014 to 2021

This paper hypothesizes that there is value in combining soil, climate and plant tissue data to give more reliable advice on nitrogen top-ups in-season when compared with models that are currently available. The benefit of soil and climate data is to factor in N mineralisation and potential yield while plant test data is a more direct approach of yield estimates when considering firstly plant N uptake from the whole soil profile and secondly biomass (important yield component). Plant test data are closer to yield in time and space than soil test data, shortening the time period for any yield prognosis …

Web-Based Training In E-Agriculture For Agricultural College, Prachyanum Nilsook, Leisa Armstrong, Pornchai Taechatanasat, Tirtha Ranjeet

Research outputs 2014 to 2021

This paper presents a web-based training system in eAgriculture for agricultural college in Thailand. The eAgriculture contents consist of introduction to information and communication technology (ICT) for agriculture, information technology in agriculture, agricultural management information system and precision farming. The research shows that the majority users are highly satisfied with the developed web-based training system. The users favoured four factors of the system including the content of the website; technical media production; the designing and the formatting of the website; and benefits of its uses.

Geospatial Data Pre-Processing On Watershed Datasets: A Gis Approach, Sreedhar Nallan, Leisa Armstrong, Barry Croke, Amiya K. Tripathy

Research outputs 2014 to 2021

Spatial data mining helps to identify interesting patterns from the spatial data sets. However, geo spatial data requires substantial data pre-processing before data can be interrogated further using data mining techniques. Multi-dimensional spatial data has been used to explain the spatial analysis and SOLAP for pre-processing data. This paper examines some of the methods for pre-processing of the data using Arc GIS 10.2 and Spatial Analyst with a case study dataset of a watershed.

The Application Of A Visual Data Mining Framework To Determine Soil, Climate And Land-Use Relationships, Yunous Vagh

Research outputs 2012

In this research study, the methodology of action research dynamics and a case study was employed in constructing a visual data mining framework for the processing and analysis of geographic land-use data in an agricultural context. The geographic data was made up of a digital elevation model (DEM), soil and land use profiles that were juxtaposed with previously captured climatic data from fixed weather stations in Australia. In this pilot study, monthly rainfall profiles for a selected study area were used to identify areas of soil variability. The rainfall was sampled for the beginning (April) of the rainy season for …