Daniel Smith

Daniel Smith
The Commonwealth Scientific and Industrial Research Organisation | CSIRO

About

75
Publications
18,925
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,063
Citations
Citations since 2017
15 Research Items
854 Citations
2017201820192020202120222023050100150200
2017201820192020202120222023050100150200
2017201820192020202120222023050100150200
2017201820192020202120222023050100150200

Publications

Publications (75)
Preprint
Self-Supervised Learning (SSL) is a new paradigm for learning discriminative representations without labelled data and has reached comparable or even state-of-the-art results in comparison to supervised counterparts. Contrastive Learning (CL) is one of the most well-known approaches in SSL that attempts to learn general, informative representations...
Preprint
Recently, Self-Supervised Representation Learning (SSRL) has attracted much attention in the field of computer vision, speech, natural language processing (NLP), and recently, with other types of modalities, including time series from sensors. The popularity of self-supervised learning is driven by the fact that traditional models typically require...
Article
Inertial motion sensors located on the animal have been used to study the behaviour of ruminant livestock. The time window size of segmented signal data can significantly affect the classification accuracy of animal behaviours. To date, there have been no studies evaluating the impact of a mixture of time window size features on the accuracy of ani...
Preprint
Change Point Detection techniques aim to capture changes in trends and sequences in time-series data to describe the underlying behaviour of the system. Detecting changes and anomalies in the web services, the trend of applications usage can provide valuable insight towards the system, however, many existing approaches are done in a supervised mann...
Article
Extracting informative and meaningful temporal segments from high-dimensional wearable sensor data, smart devices, or IoT data is a vital preprocessing step in applications such as Human Activity Recognition (HAR), trajectory prediction, gesture recognition, and lifelogging. In this paper, we propose ESPRESSO (Entropy and ShaPe awaRe timE-Series Se...
Preprint
Extracting informative and meaningful temporal segments from high-dimensional wearable sensor data, smart devices, or IoT data is a vital preprocessing step in applications such as Human Activity Recognition (HAR), trajectory prediction, gesture recognition, and lifelogging. In this paper, we propose ESPRESSO (Entropy and ShaPe awaRe timE-Series Se...
Article
An on-animal sensor based research tool is currently being developed to support research studies of dystocia in lambing ewes. Given dystocia is associated with a prolonged period of parturition, the tool is being developed with the intention to automatically estimate the duration of parturition using motion data from a 3-axis accelerometer fitted t...
Article
Breeding for resistance to gastrointestinal nematodes (GIN) in sheep relies largely on the use of worm egg counts (WEC) to identify animals that are able to resist infection. As an alternative to such measures of parasite load we aimed to develop a method to identify animals showing resistance to GIN infection based on the impact of the infection o...
Conference Paper
Designing engaging interfaces for young children poses a significant research challenge. In two studies we evaluated two different tablet computer prototypes of a tool designed to assist non-experts in administering a speech assessment and to support them in their referral decisions. The development of this application builds on our research and co...
Article
Full-text available
Practical and reliable measurement of pasture intake by individual animals will enable improved precision in livestock and pasture management, provide input data for prediction and simulation models, and allow animals to be ranked on grazing efficiency for genetic improvement. In this study, we assessed whether pasture intake of individual grazing...
Article
Full-text available
In this paper, we summarise the outcome of a set of experiments aimed at classifying cattle behaviour based on sensor data. Each animal carried sensors generating time series accelerometer data placed on a collar on the neck at the back of the head, on a halter positioned at the side of the head behind the mouth, or on the ear using a tag. The purp...
Article
Precision management systems for livestock offer the potential to monitor and manage animals on an individual basis. A key component of these sensor based systems are the analytical models that automatically translate sensor data into different behavioral categories. A new methodology was proposed for multi-class behavior modeling based upon the “o...
Article
This study was conducted to investigate the detection of heat events in pasture-based dairy cows fitted with on-animal sensors using unsupervised learning. Accelerometer data from the cow collars were used to identify increased activity levels in cows associated with recorded heat events. Time series data from the accelerometers were first segmente...
Conference Paper
Full-text available
One in twenty Australian children suffers from a speech disorder. Early detection of such problems can significantly improve literacy and academic outcomes for these children, reduce health and educational burden and ongoing social costs. Here we present the development of a prototype and feasibility tests of a screening and decision support tool t...
Article
Full-text available
One in twenty Australian children suffers from a speech disorder. Early detection of such problems can significantly improve literacy and academic outcomes for these children, reduce health and educational burden and ongoing social costs. Here we present the development of a prototype and feasibility tests of a screening and decision support tool t...
Article
Models were developed to classify six different behaviours for a group of seven steers fitted with an accelerometer and pressure sensor. As part of the process, a greedy feature selection method was used to identify the most discriminatory inputs from a diverse set of statistical, spectral and information theory based features. The study showed the...
Article
Full-text available
An in situ optical oyster heart rate sensor generates signals requiring frequency estimation with properties different to human ECG and speech signals. We discuss the method of signal generation and highlight a number of these signal properties. An optimal heart rate estimation approach was identified by application of a variety of frequency estima...
Article
Full-text available
Despite ongoing reduction in genotyping costs, genomic studies involving large numbers of species with low economic value (such as Black Tiger prawns) remain cost prohibitive. In this scenario DNA pooling is an attractive option to reduce genotyping costs. However, genotyping of pooled samples comprising DNA from many individuals is challenging due...
Article
In this paper a novel application of salad leaf disease detection has been developed using a combination of big data analytics and on field multi-dimensional sensing. Heterogeneous knowledge integration from publicly available various big data sources, calibrated with in-situ ground truth information, has the merit to be a very efficient way to tac...
Article
The costs associated with developing high density microarray technologies are prohibitive for genotyping animals when there is low economic value associated with a single animal (e.g. prawns). DNA pooling is an attempt to address this issue by combining multiple DNA samples prior to genotyping. Instead of genotyping the DNA samples of the individua...
Conference Paper
This paper aims to develop big data based knowledge recommendation framework architecture for sustainable precision agricultural decision support system using Computational Intelligence (Machine Learning Analytics) and Semantic Web Technology (Ontological Knowledge Representation). Capturing domain knowledge about agricultural processes, understand...
Article
Passive acoustics represent a low-cost approach to detecting and avoiding other marine vehicles using limited computing and power resources. We present a robust safety behavior for long-term environmental sensing of rivers and estuaries demonstrated on a smartphone-driven, diving robot. The detection method is based on energy detection from the hyd...
Article
In this paper various supervised machine learning techniques were applied to classify cattle behaviour patterns recorded using collar systems with 3-axis accelerometer and magnetometer, fitted to individual dairy cows to infer their physical behaviours. Cattle collar data was collected at the Tasmanian Institute of Agriculture (TIA) Dairy Research...
Article
In this paper, two new multivariate time series classifiers are introduced as the Bag of Class Posteriors (BOCP) and the Bag of Class Posterior with Ordering (BOCPO). The models propose a new multi-scale feature representation where the class posterior estimates of contiguous local patterns are aggregated over longer time scales. The models are emp...
Conference Paper
A preliminary study is undertaken to determine whether the fast neutron counts of a cosmic ray probe can be used as proxy estimate of green biomass over its 40 hectare measurement area. The study was conducted using the Normalized Difference Vegetation Index (NDVI) product from NASA MODIS satellite imagery and pressure corrected fast neutron counts...
Conference Paper
In this paper a novel remote sensing data integration framework has been developed using ensemble machine learning to estimate large area wise ground water balance. Heterogeneous spatio-temporal database including 'Australian Water Availability Project (AWAP) database', 'Australian Digital Elevation data (ADED), and 'NASA MODIS Vegetation Index (VI...
Conference Paper
In this paper supervised machine learning techniques based multi-classifier pattern recognition system was developed and applied to classify cattle behavioural patterns recorded using collar systems fitted to individual dairy cows to infer their feeding behaviors. Cattle tag sensory system, consist of a piezoelectric micro-electromechanical chip co...
Conference Paper
In this paper a novel application of salad leaf disease detection has been developed using a combination of machine learning algorithms and Hyper Spectral sensing. Various field experiments were conducted to acquire different vegetation reflectance spectrum profiles using a portable high resolution ASD FieldSpec4 Spectroradiometer, at a farm locate...
Conference Paper
Full-text available
New sensor streams are being generated at a rapidly increasing rate. The sources of these streams are a diverse set of networked sensors, diverse both in sensing hardware and sensing modality. Machine learning algorithms are ideally placed to develop generalized methods for stream analysis. One exemplar problem is the detection and analysis of peri...
Conference Paper
Full-text available
The combination of low density SNP arrays and DNA pooling is a fast and cost effective approach to genotyping that opens up basic genomics to a range of new applications and studies. However we have identified significant limitations in the existing approach to calculating allele frequencies with DNA pooling. These limitations include a reduced abi...
Conference Paper
Full-text available
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), Guide...
Conference Paper
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 s...
Article
A novel machine learning approach to assess the quality of sensor data using an ensemble classification framework is presented in this paper. The quality of sensor data is indicated by discrete quality flags that indicate the level of uncertainty associated with a sensor reading. Depending on the domain and the problem under consideration, the leve...
Article
Full-text available
The National Reference Station (NRS) network, part of Australia’s Integrated Marine Observing System (IMOS), is designed to provide the baseline multi-decadal time series required to understand how large-scale, long-term change and variability in the global ocean are affecting Australia’s coastal ocean ecosystems. High temporal resolution observati...
Article
The feeding inefficiencies associated with intensively cultured prawn systems have a significant financial cost and environmental impact. Initial trials of a commercial system using sound to manage feeding within cultured systems have achieved promising results with an impressive food conversion (food weight/biomass) ratio of 1.42. Whilst these res...
Article
Two sound classifiers were proposed for a novel aquaculture application that involved processing sound to estimate the feed consumption of prawns within the turbid waters of farm ponds. A two stage content classifier inferred feed events using identified sound features. To deal with the class ambiguity created by the acoustically challenging condit...
Article
Full-text available
Before using remote data sources, or those from external organisations, it is important to establish if the source is fit for purpose. We have developed an approach to automatic sensor data annotation and visualisation that evaluates overall sensor network performance and data quality. The CSIRO’s South Esk hydrological sensor web combines data rel...
Conference Paper
Full-text available
In this paper we present a novel application of genetic algorithm for obtaining mineral domains. An important step in mineral exploration is to identify potential underground areas for mining purposes. Cylindrical cores of rock are extracted from the subsurface using diamond drilling and data is logged on the cores leading to geo-data sets. These g...
Conference Paper
We investigate the impact of including context features with conventional machine learning models for energy disaggregation. Four types of context features that were broadly categorized as either temporal context or activity based context were individually examined across ten class of household appliance. We demonstrate that all machine learning mo...
Conference Paper
This research study focused on automatic sensor data annotation and visualisation of dynamic weather data acquired from a large sensor network. The aim was to develop a data visualisation method for CSIRO's South Esk hydrological sensor web to evaluate the overall network performance and provide visual data quality assessment. The visual data quali...
Conference Paper
Numerous sources of uncertainty are associated with the data acquisition process in marine sensor networks. It is thus required to assure that the data quality of sensors is fit for the intended purpose. We propose a supervised learning framework to infer the quality of sensor observations online. A problem with using supervised classification in q...
Article
Full-text available
Online automated quality assessment is critical to determine a sensor's fitness for purpose in real-time applications. A Dynamic Bayesian Network (DBN) framework is proposed to produce probabilistic quality assessments and represent the uncertainty of sequentially correlated sensor readings. This is a novel framework to represent the causes, qualit...
Article
Full-text available
The automated collection of data (e.g., through sensor networks) has led to a massive increase in the quantity of environmental and other data available. The sheer quantity of data and growing need for real-time ingestion of sensor data (e.g., alerts and forecasts from physical models) means that automated Quality Assurance/Quality Control (QA/QC)...
Article
The manual Quality Control (QC) process undertaken by experts in marine sensor deployments is becoming increasingly impractical as the size of these deployments increase and streaming applications become the norm. Automated quality control procedures have been developed for real-time sensor deployments proposing a range of tests and checks. Althoug...
Chapter
The rapid growth in sensor and ubiquitous device deployments has resulted in an explosion in the availability of data. The concept of the Sensor Web has provided a web-based information sharing platform to allow different organisations to share their sensor offerings. We compare the Open Geospatial Consortium - Sensor Web Enablement(OGC-SWE) with M...
Article
Full-text available
Signal processing applications use sinusoidal modelling for speech synthesis, speech coding, and audio coding. Estimation of the model parameters involves non-linear optimisation methods, which can be very costly for real-time applications. We propose a low-complexity iterative method that starts from initial frequency estimates and converges rapid...
Article
Full-text available
An onset detection system that exploits MPEG-7 audio descriptors is proposed in this paper, with investigations into the feasibility of MPEG-7 based onset detection performed across a diverse database of music. Detection func-tions were developed from both individual MPEG-7 descriptors and combinations of descriptors (joint detection functions). Th...
Conference Paper
Base station mobility can be exploited to minimise the energy consumption in a wireless sensor network. This paper investigates the impact that base station movement has upon the performance of cluster-based wireless sensor networks. Three types of base station movement are considered: movement influenced by the position of cluster-heads, random mo...
Conference Paper
We propose a novel approach to automating soil texture classification from in situ sensors in the field. This approach exploits the features of a soil water retention model using machine learning algorithms. Knowledge of the soil textures is then used to learn the composition of the field and its soil horizons. We discuss the role of soil texture c...
Conference Paper
The sensor Web is a distributed sensing system in which information is shared globally. The emergence of this technology will enable the integration of different sensing platforms with temporal and spatial variability. This has a potential to revolutionise hydrological monitoring and forecasting. Our project will establish a sensor Web test bed in...
Conference Paper
Full-text available
The technological demands required to successfully practice either targeted irrigation control and/or deficit irrigation strategies are currently reliant on numerical models which are often underutilised due to their complexity and low operational focus. A simple and practical real-time control system is proposed using a model-data fusion approach,...
Conference Paper
A novel shape recognition algorithm was developed to autonomously classify the Northern Pacific Sea Star (Asterias amurenis) from benthic images that were collected by the Starbug AUV during 6km of transects in the Derwent estuary. Despite the effects of scattering, attenuation, soft focus and motion blur within the underwater images, an optimal jo...
Conference Paper
Full-text available
Sinusoidal parameter estimation is a computationally-intensive task, which can pose prob-lems for real-time implementations. In this paper, we propose a low-complexity iterative method for estimating sinusoidal parameters that is based on the linearisation of the model around an initial frequency estimate. We show that for N sinusoids in a frame of...
Article
A blind signal separation algorithm (SCAtemp) that exploits both the sparse time-frequency representation and temporal structure of speech is proposed. SCAtemp compares each speech signal's adherence to the sparsity and temporal criteria, before switching to the most appropriate criteria to estimate each signal. This algorithm is shown to improve t...
Article
Blind Signal Separation (BSS) techniques are commonly employed in the separation of speech signals, using Independent Component Analysis (ICA) as the criterion for separation. This paper investigates the viability of employing ICA for real-time speech separation (where short frame sizes are the norm). The relationship between the statistics of spee...
Conference Paper
A sequential approach to sparse component analysis (SeqTIF) is proposed in this paper. Although SeqTIF employs the estimation process of the simultaneous TIFROM algorithm, a source cancellation and deflation technique are also incorporated to sequentially estimate speech signals in the mixture. Results indicate that SeqTIF's separation performance...
Article
Full-text available
We propose a new blind signal separation (BSS) technique, developed specifically for speech, that exploits a priori knowledge of speech production mechanisms. In our approach, the autoregressive (AR) structure and fundamental frequency (F0) production mechanisms of speech are jointly modeled. We compare the separation performance of our joint AR-F0...
Conference Paper
Full-text available
This paper investigates the performance of blind signal separation (BSS) algorithms that exploit the temporal pre-dictability of speech. Specifically, the investigation considers how the separation performance of two BSS algorithms will be affected when the length of the AR process (used in the algorithms to model speech) is varied. The investigati...
Conference Paper
TIFCORR is a Blind Signal Separation technique that is well suited to separating audio signals, requiring each signal to be sparse in only a local time-frequency region of their representation [1]. TIFCORR can suffer from inconsistencies in mixing system estimation, thus we present a modified algorithm incorporating k-means clustering [2] to improv...
Article
Full-text available
TIFROM [1, 2] is a two channel separation technique, which is well suited to separating audio signals, and in particular, depen-dent signals that fall outside the scope of conventional BSS appli-cations [1]. One problem with TIFROM however, is degraded per-formance due to inconsistent estimation of the mixing system. To reduce these inconsistencies...
Article
Full-text available
The 'cocktail party problem' is the term commonly used to describe the perceptual problem experienced by a listener who attempts to focus upon a single speaker in a scene of interfering audio and noise sources. Blind Signal Separation (BSS) is a blind identification approach that can offer an adaptive, intelligent solution to the 'cocktail party pr...

Network

Cited By

Projects

Project (1)