Ahsan Morshed

Internet of Things Platform for Smart Farming: Experiences and Lessons Learnt

Improving farm productivity is essential for increasing farm profitability and meeting the rapidly growing demand for food that is fuelled by rapid population growth across the world. Farm productivity can be increased by understanding and forecasting crop performance in a variety of environmental conditions. Crop recommendation is currently based on data collected in field-based agricultural studies that capture crop performance under a variety of conditions (e.g., soil quality and environmental conditions). However, crop performance data collection is currently slow, as such crop studies are often undertaken in remote and distributed locations, and such data are typically collected manually. Furthermore, the quality of manually collected crop performance data is very low, because it does not take into account earlier conditions that have not been observed by the human operators but is essential to filter out collected data that will lead to invalid conclusions (e.g., solar radiation readings in the afternoon after even a short rain or overcast in the morning are invalid, and should not be used in assessing crop performance). Emerging Internet of Things (IoT) technologies, such as IoT devices (e.g., wireless sensor networks, network-connected weather stations, cameras, and smart phones) can be used to collate vast amount of environmental and crop performance data, ranging from time series data from sensors, to spatial data from cameras, to human observations collected and recorded via mobile smart phone applications. Such data can then be analysed to filter out invalid data and compute personalised crop recommendations for any specific farm. In this paper, we present the design of SmartFarmNet, an IoT-based platform that can automate the collection of environmental, soil, fertilisation, and irrigation data; automatically correlate such data and filter-out invalid data from the perspective of assessing crop performance; and compute crop forecasts and personalised crop recommendations for any particular farm. SmartFarmNet can integrate virtually any IoT device, including commercially available sensors, cameras, weather stations, etc., and store their data in the cloud for performance analysis and recommendations. An evaluation of the SmartFarmNet platform and our experiences and lessons learnt in developing this system concludes the paper. SmartFarmNet is the first and currently largest system in the world (in terms of the number of sensors attached, crops assessed, and users it supports) that provides crop performance analysis and recommendations.

Recommending environmental knowledge as linked open data cloud using semantic machine learning

Large scale environmental knowledge integration and development of a knowledge recommendation system for the Linked Open Data Cloud using semantic machine learning approach was the main mission of this research. This study considered five different environmental big data sources including SILO, AWAP, ASRIS, MODIS and CosmOz complementary for knowledge integration. Unsupervised clustering techniques based on principal component analysis (PCA) and Fuzzy-C-Means (FCM) and Self-organizing map (SOM) clustering was used to learn the extracted features and to create a 2D map based dynamic knowledge recommendation system. Knowledge was stored in a triplestore using triples format (subject, predicate, and object) along with the complete meta-data provenance information. The Resource Description Framework (RDF) representation made i-EKbase very flexible to integrate with the Linked Open Data (LOD) cloud. The developed Intelligent Environmental Knowledgebase (i-EKbase) could be used for any environmental decision support application.

Performance Evaluation of South Esk Hydrological Sensor Web: Unsupervised Machine Learning and Semantic Linked Data Approach

Technological progress has lead the sensor network domain to an era where environmental and agricultural domain applications are completely dependent on hydrological sensor networks. Data from the sensor networks are being used for knowledge management and critical decision support system. The quality of data can, however, vary widely. Existing automated quality assurance approach based on simple threshold rulebase could potentially miss serious errors requiring robust and complex domain knowledge to identify. This paper proposes a linked data concept, unsupervised pattern recognition, and semantic ontologies based dynamic framework to assess the reliability of hydrological sensor network and evaluate the performance of the sensor network. Newly designed framework is used successfully to evaluate the South Esk hydrological sensor web in Tasmania, indicating that domain ontology based linked data approach could be a very useful methodology for quality assurance of the complex data.

Environmental Spatio-temporal Ontology for the Linked Open Data Cloud

The rapid access of sensor technology provides both challenges and opportunities to authenticated spatiotemporal data. Authentication can be assured by developing related ontologies. Ontology explicitly specifies shared conceptualization and formal vocabularies. In this paper, we proposed an environmental spatio-temporal ontology (ESTO) using unified resource description framework (RDF) and Intelligent Environmental Knowledgebase (i-EKbase) recommendation system. Five different environmental data sources namely SILO, AWAP, ASRIS, CosmOz, and MODIS were considered to develop i-EKbase where knowledge was integrated. The recommendation system was founded on web based large scale dynamic data mining, contextual knowledge extraction, and integrated knowledge representation. The proposed ESTO was tested for optimization of the accessibility and usability issues related to big data sets and minimize the overall application costs. RDF representation made this ontology very flexible to publish on Linked Open Data Cloud environment.

An investigation of cow feeding behavior using motion sensors

An experiment to study the impact of supplements upon the feeding behavior of dairy cattle was conducted at the Tasmanian Institute of Agriculture (TIA) Dairy Research Facility. Collar systems with 3-axis accelerometer and magnetometer were fitted to individual cows to infer their feeding behavior. We describe the solutions applied to correct for sensor data issues, and then provide some preliminary analysis associated with developing behavior models using multivariate time series data.

Mobile application based sustainable irrigation water usage decision support system: An intelligent sensor CLOUD approach

In this paper a novel data integration approach based on three environmental Sensors - Model Networks (including the Bureau of Meteorology-SILO database, Australian Cosmic Ray Sensor Network database (CosmOz), and Australian Water Availability Project (AWAP) database) has been proposed to estimate ground water balance and average water availability. An unsupervised machine learning based clustering technique (Dynamic Linear Discriminant Analysis (D-LDA)) has been applied for extracting knowledge from the large integrated database. The Commonwealth Scientific and Industrial Research Organisation (CSIRO) Sensor CLOUD computing infrastructure has been used extensively to process big data integration and the machine learning based decision support system. An analytical outcome from the Sensor CLOUD is presented as dynamic web based knowledge recommendation service using JSON file format. An intelligent ANDROID based mobile application has been developed, capable of automatically communicating with the Sensor CLOUD to get the most recent daily irrigation, water requirement for a chosen location and display the status in a user friendly traffic light system. This recommendation could be used directly by the farmers to make the final decision whether to buy extra water for irrigation or not on a particular day.

Machine Learning based Vocabulary Management Tool Assessment for the Linked Open Data

domain vocabularies in the context of developing the knowledge based Linked Open data system is the most important discipline on the web. Many editors are available for developing and managing the vocabularies or Ontologies. However, selecting the most relevant editor is very difficult since each vocabulary construction initiative requires its own budget, time, resources. In this paper a novel unsupervised machine learning based comparative assessment mechanism has been proposed for selecting the most relevant editor. Defined evaluation criterions were functionality, reusability, data storage, complexity, association, maintainability, resilience, reliability, robustness, learnability, availability, flexibility, and visibility. Principal component analysis (PCA) was applied on the feedback data set collected from a survey involving sixty users. Focus was to identify the least correlated features carrying the most independent information variance to optimize the tool selection process. An automatic evaluation method based on Bagging Decision Trees has been used to identify the most suitable editor. Three tools namely Vocbench, TopBraid EVN and Pool Party Thesaurus Manager have been evaluated. Decision tree based analysis recommended the Vocbench and the Pool Party Thesaurus Manager are the better performer than the TopBraid EVN tool with very similar recommendation scores.

Autonomous Framework for Sensor Network Quality Annotation: Maximum Probability Clustering Approach

Abstract In this paper an autonomous feature clustering framework has been proposed for performance and reliability evaluation of an environmental sensor network. Environmental time series were statistically preprocessed to extract multiple semantic features. A novel hybrid clustering framework was designed based on Principal Component Analysis (PCA), Guided Self-Organizing Map (G-SOM), and Fuzzy-C-Means (FCM) to cluster the historical multi-feature space into probabilistic state classes. Finally a dynamic performance annotation mechanism was developed based on Maximum (Bayesian) Probability Rule (MPR) to quantify the performance of an individual sensor node and network. Based on the results from this framework, a “data quality knowledge map” was visualized to demonstrate the effectiveness of this framework.

Development of an intelligent environmental knowledge recommendation system for sustainable water resource management using modis satellite imagery

With the global availability and accessibility of environmental data sources it is possible to address the water related problems. Locally, in the Australian context, the water industry is in a unique position due to the extremes with a vast experience of drought and flood conditions. Water in Australia is a national priority and there is a need to develop an accurate and timely decision support system regarding efficient and optimal water usage. To address this issue, in this paper, we proposed an integrated environmental knowledge recommendation system based on large scale dynamic web data mining and contextual knowledge integration to provide an expert water resource management solution. We integrated five different environmental data sources namely SILO, AWAP, ASRIS, CosmOz, and MODIS imagery to develop and test the proposed knowledge recommendation framework called intelligent Environmental knowledgebase (i-Ekbase). The developed system was tested for its robustness and applicability.

Robot sensor data interoperability and tasking with semantic technologies

In large-scale monitoring programs, such as in agriculture and environmental management, field robots have potentially lower cost and technical overhead than multiple static sensors. Robot sensing data, however, is not generally shared during, or after deployment. This is a wasted opportunity for enhancing autonomous decision making in the robot with external data, or for providing potentially useful data to other systems. We present how semantic technologies; including Linked Open Data principles and ontologies can assist by improving robot data interoperability.