scholarly journals Livestock Informatics Toolkit: A Case Study in Visually Characterizing Complex Behavioral Patterns across Multiple Sensor Platforms, Using Novel Unsupervised Machine Learning and Information Theoretic Approaches

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 1
Author(s):  
Catherine McVey ◽  
Fushing Hsieh ◽  
Diego Manriquez ◽  
Pablo Pinedo ◽  
Kristina Horback
Keyword(s):  
Machine Learning ◽  
Linear Models ◽  
Sensor Data ◽  
Behavioral Patterns ◽  
Time Budgets ◽  
Livestock Farming ◽  
Unsupervised Machine Learning ◽  
Information Theoretic ◽  
Sensor Platforms ◽  
Using Data

Large and densely sampled sensor datasets can contain a range of complex stochastic structures that are difficult to accommodate in conventional linear models. This can confound attempts to build a more complete picture of an animal’s behavior by aggregating information across multiple asynchronous sensor platforms. The Livestock Informatics Toolkit (LIT) has been developed in R to better facilitate knowledge discovery of complex behavioral patterns across Precision Livestock Farming (PLF) data streams using novel unsupervised machine learning and information theoretic approaches. The utility of this analytical pipeline is demonstrated using data from a 6-month feed trial conducted on a closed herd of 185 mix-parity organic dairy cows. Insights into the tradeoffs between behaviors in time budgets acquired from ear tag accelerometer records were improved by augmenting conventional hierarchical clustering techniques with a novel simulation-based approach designed to mimic the complex error structures of sensor data. These simulations were then repurposed to compress the information in this data stream into robust empirically-determined encodings using a novel pruning algorithm. Nonparametric and semiparametric tests using mutual and pointwise information subsequently revealed complex nonlinear associations between encodings of overall time budgets and the order that cows entered the parlor to be milked.

Towards Behaviour Recognition with Unlabelled Sensor Data

2013 ◽  
pp. 86-110
Author(s):  
Sook-Ling Chua ◽  
Stephen Marsland ◽  
Hans W. Guesgen
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Inverse Problem ◽  
Sensor Data ◽  
Training Set ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Using Data ◽  
Symbolic Approach ◽  
Behaviour Recognition

The problem of behaviour recognition based on data from sensors is essentially an inverse problem: given a set of sensor observations, identify the sequence of behaviours that gave rise to them. In a smart home, the behaviours are likely to be the standard human behaviours of living, and the observations will depend upon the sensors that the house is equipped with. There are two main approaches to identifying behaviours from the sensor stream. One is to use a symbolic approach, which explicitly models the recognition process. Another is to use a sub-symbolic approach to behaviour recognition, which is the focus in this chapter, using data mining and machine learning methods. While there have been many machine learning methods of identifying behaviours from the sensor stream, they have generally relied upon a labelled dataset, where a person has manually identified their behaviour at each time. This is particularly tedious to do, resulting in relatively small datasets, and is also prone to significant errors as people do not pinpoint the end of one behaviour and commencement of the next correctly. In this chapter, the authors consider methods to deal with unlabelled sensor data for behaviour recognition, and investigate their use. They then consider whether they are best used in isolation, or should be used as preprocessing to provide a training set for a supervised method.

scholarly journals Machine-Learning Powered Optoacoustic Sensor for Diabetes Progression

2021 ◽  
Author(s):  
Pouyan Mohajerani ◽  
Juan Aguirre ◽  
Murad Omar ◽  
Hailong He ◽  
Angelos Karlas ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Window ◽  
Sensor Data ◽  
Vascular Density ◽  
Atherosclerotic Cardiovascular Disease ◽  
Technical Parameters ◽  
Sensor Performance ◽  
Clinical Complications ◽  
Patient Groups ◽  
Using Data

AbstractThe assessment of diabetes severity relies primarily on a count of clinical complications to empirically characterize disease. Disease staging based on clinical complications also employs a scoring system that may not be optimally suited for analysis of earlier stages of diabetes development or for monitoring smaller increments of disease progress with high precision. We propose a novel sensor, which goes beyond the abilities of current state-of-the-art approaches and introduces a new concept in the assessment of biomedical markers by means of ultra-broadband optoacoustic detection. Being insensitive to photon scattering, the new sensor can resolve optical biomarkers in fine detail and as a function of depth and relates epidermal and dermal morphological and micro-vascular density features to diabetes state. We demonstrate basic sensor characteristics in phantoms and examine the novel sensing concept presented in a pilot study using data from 86 participants (20 healthy and 66 diabetic) at an ultra-wide optoacoustic bandwidth of 120 MHz. Machine learning based on ensemble trees was developed and trained in a supervised fashion and subsequently used to examine the relation of sensor data to disease severity, in particular as it associates to diabetes without complications vs. diabetic neuropathy or atherosclerotic cardiovascular disease. We also investigated the sensor performance in relation to HbA1C values. The proposed method achieved statistically significant detection in all different patient groups. The effect of technical parameters, in particular sensor area size and the time window of optoacoustic signals used in data training were also examined in measurements from phantoms and humans. We discuss how optoacoustic sensors fundamentally solve limitations present in optical sensing and, empowered by machine learning, open a new chapter in non-invasive portable sensing for biomedical applications.

scholarly journals Unsupervised Learning for Product Use Activity Recognition: An Exploratory Study of a “Chatty Device”

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 4991
Author(s):  
Mike Lakoju ◽  
Nemitari Ajienka ◽  
M. Ahmadieh Khanesar ◽  
Pete Burnap ◽  
David T. Branson
Keyword(s):  
Machine Learning ◽  
Activity Recognition ◽  
Sampling Rate ◽  
Machine Learning Algorithms ◽  
Data Driven ◽  
Sensor Data ◽  
Unsupervised Machine Learning ◽  
Fuzzy C Means ◽  
Product Use ◽  
Fuzzy C Means Algorithm

To create products that are better fit for purpose, manufacturers require new methods for gaining insights into product experience in the wild at scale. “Chatty Factories” is a concept that explores the transformative potential of placing IoT-enabled data-driven systems at the core of design and manufacturing processes, aligned to the Industry 4.0 paradigm. In this paper, we propose a model that enables new forms of agile engineering product development via “chatty” products. Products relay their “experiences” from the consumer world back to designers and product engineers through the mediation provided by embedded sensors, IoT, and data-driven design tools. Our model aims to identify product “experiences” to support the insights into product use. To this end, we create an experiment to: (i) collect sensor data at 100 Hz sampling rate from a “Chatty device” (device with sensors) for six common everyday activities that drive produce experience: standing, walking, sitting, dropping and picking up of the device, placing the device stationary on a side table, and a vibrating surface; (ii) pre-process and manually label the product use activity data; (iii) compare a total of four Unsupervised Machine Learning models (three classic and the fuzzy C-means algorithm) for product use activity recognition for each unique sensor; and (iv) present and discuss our findings. The empirical results demonstrate the feasibility of applying unsupervised machine learning algorithms for clustering product use activity. The highest obtained F-measure is 0.87, and MCC of 0.84, when the Fuzzy C-means algorithm is applied for clustering, outperforming the other three algorithms applied.

Monitoring bed level dynamics in mangrove wetlands by Laster ranging technique

2020 ◽  
Author(s):  
Zhan Hu ◽  
Juanling Zhou ◽  
Yisheng Peng
Keyword(s):  
Machine Learning ◽  
Low Cost ◽  
Measurement Data ◽  
Tidal Flats ◽  
Surface Elevation ◽  
Sensor Data ◽  
Analytical Models ◽  
Measuring Point ◽  
New Instrument ◽  
Using Data

<p>Climate change-related temperature increases and sea-level rises have a significant impact on coastal environment. The morphodynamic processes on tidal flats under this global change have been studied by many numerical and analytical models. Studies on morphodynamic processes requires accurate bed-level measurement data to reflect the complex intertidal morphodynamics. The newly-developed SED sensor (Surface Elevation Dynamics sensor) has been introduced to provide continuous long-term monitoring with relatively low cost of labor and acquisition. However, when in use, the instrument is inserted directly to the ground, inducing scour pits around measuring point. Thus, we introduce a new instrument which make use of laser ranging called LSED (Laster based Surface Elevation Dynamics) sensor. It could avoid touching the bed surface and obtain data with 1-millimeter vertical resolution. The developed sensors can be installed at both bare and vegetated tidal flats to monitoring short-term bed level changes under different settings. In light of this, we set up a group of Laser-SED sensors in National Mangroves Park in Hailing island, Yangjiang. Firstly, these new instruments were tested using data obtained from LSED sensors and traditional Sediment Erosion Bars. An excellent agreement in these measurement methods indicating that LSED sensors are reliable in bed-level measurements. The obtained LSED-sensor data was subsequently used to develop machine learning predictors, which revealed the main drivers of the accumulative and daily bed-level changes. We conclude that the LSED-sensors can further support machine learning applications to extract new knowledge on coastal biogeomorphic processes.</p>

scholarly journals Employing Multimodal Machine Learning for Stress Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Rahee Walambe ◽  
Pranav Nayak ◽  
Ashmit Bhardwaj ◽  
Ketan Kotecha
Keyword(s):  
Machine Learning ◽  
Multimodal Fusion ◽  
Sensor Data ◽  
Behavioral Patterns ◽  
Health Issues ◽  
Stress Detection ◽  
Mental Strain ◽  
Stress Levels ◽  
Mental Wellness ◽  
And Performance

In the current information age, the human lifestyle has become more knowledge-oriented, leading to sedentary employment. This has given rise to a number of health and mental disorders. Mental wellness is one of the most neglected, however crucial, aspects of today’s fast-paced world. Mental health issues can, both directly and indirectly, affect other sections of human physiology and impede an individual’s day-to-day activities and performance. However, identifying the stress and finding the stress trend for an individual that may lead to serious mental ailments is challenging and involves multiple factors. Such identification can be achieved accurately by fusing these multiple modalities (due to various factors) arising from a person’s behavioral patterns. Specific techniques are identified in the literature for this purpose; however, very few machine learning-based methods are proposed for such multimodal fusion tasks. In this work, a multimodal AI-based framework is proposed to monitor a person’s working behavior and stress levels. We propose a methodology for efficiently detecting stress due to workload by concatenating heterogeneous raw sensor data streams (e.g., face expressions, posture, heart rate, and computer interaction). This data can be securely stored and analyzed to understand and discover personalized unique behavioral patterns leading to mental strain and fatigue. The contribution of this work is twofold: firstly, proposing a multimodal AI-based strategy for fusion to detect stress and its level and, secondly, identifying a stress pattern over a period of time. We were able to achieve 96.09% accuracy on the test set in stress detection and classification. Further, we were able to reduce the stress scale prediction model loss to 0.036 using these modalities. This work can prove important for the community at large, specifically those working sedentary jobs, to monitor and identify stress levels, especially in current times of COVID-19.

scholarly journals Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants

2017 ◽  
Author(s):  
Matthew Willetts ◽  
Sven Hollowell ◽  
Louis Aslett ◽  
Chris Holmes ◽  
Aiden Doherty
Keyword(s):  
Public Health ◽  
Physical Activity ◽  
Machine Learning ◽  
Markov Models ◽  
Activity Patterns ◽  
Sleep Time ◽  
Sensor Data ◽  
Statistical Machine Learning ◽  
Using Data ◽  
Objectively Measured

ABSTRACTCurrent public health guidelines on physical activity and sleep duration are limited by a reliance on subjective self-reported evidence. Using data from simple wrist-worn activity monitors, we developed a tailored machine learning model, using balanced random forests with Hidden Markov Models, to reliably detect a number of activity modes. We show that physical activity and sleep behaviours can be classified with 87% accuracy in 159,504 minutes of recorded free-living behaviours from 132 adults. These trained models can be used to infer fine resolution activity patterns at the population scale in 96,220 participants. For example, we find that men spend more time in both low- and high-intensity behaviours, while women spend more time in mixed behaviours. Walking time is highest in spring and sleep time lowest during the summer. This work opens the possibility of future public health guidelines informed by the health consequences associated with specific, objectively measured, physical activity and sleep behaviours.

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

2017 ◽  
Author(s):  
Sabrina Jaeger ◽  
Simone Fulle ◽  
Samo Turk
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Learning Approaches ◽  
Unsupervised Machine Learning ◽  
Feature Representations ◽  
Machine Learning Approach ◽  
The Individual ◽  
Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

Analysis of the Bath Motion in the MM-SQC Dynamics Using Unsupervised Machine Learning Dimensionality Reduction Approaches: Principal Component Analysis

2020 ◽  
Author(s):  
Jiawei Peng ◽  
Yu Xie ◽  
Deping Hu ◽  
Zhenggang Lan
Keyword(s):  
Machine Learning ◽  
Principal Component Analysis ◽  
Collective Motion ◽  
Principal Component ◽  
Component Analysis ◽  
Nonadiabatic Dynamics ◽  
Trajectory Data ◽  
Unsupervised Machine Learning ◽  
Physical Knowledge ◽  
Vibronic Couplings

The system-plus-bath model is an important tool to understand nonadiabatic dynamics for large molecular systems. The understanding of the collective motion of a huge number of bath modes is essential to reveal their key roles in the overall dynamics. We apply the principal component analysis (PCA) to investigate the bath motion based on the massive data generated from the MM-SQC (symmetrical quasi-classical dynamics method based on the Meyer-Miller mapping Hamiltonian) nonadiabatic dynamics of the excited-state energy transfer dynamics of Frenkel-exciton model. The PCA method clearly clarifies that two types of bath modes, which either display the strong vibronic couplings or have the frequencies close to electronic transition, are very important to the nonadiabatic dynamics. These observations are fully consistent with the physical insights. This conclusion is obtained purely based on the PCA understanding of the trajectory data, without the large involvement of pre-defined physical knowledge. The results show that the PCA approach, one of the simplest unsupervised machine learning methods, is very powerful to analyze the complicated nonadiabatic dynamics in condensed phase involving many degrees of freedom.

Sign in / Sign up

Export Citation Format

Share Document