Machine learning for activity recognition : hip versus wrist data

Problem addressed Wrist-worn accelerometers are associated with greater compliance. However, validated algorithms for predicting activity type from wrist-worn accelerometer data are lacking. This study compared the activity recognition rates of an activity classifier trained on acceleration signal collected on the wrist and hip. Methodology 52 children and adolescents (mean age 13.7 +/- 3.1 year) completed 12 activity trials that were categorized into 7 activity classes: lying down, sitting, standing, walking, running, basketball, and dancing. During each trial, participants wore an ActiGraph GT3X+ tri-axial accelerometer on the right hip and the non-dominant wrist. Features were extracted from 10-s windows and inputted into a regularized logistic regression model using R (Glmnet + L1). Results Classification accuracy for the hip and wrist was 91.0% +/- 3.1% and 88.4% +/- 3.0%, respectively. The hip model exhibited excellent classification accuracy for sitting (91.3%), standing (95.8%), walking (95.8%), and running (96.8%); acceptable classification accuracy for lying down (88.3%) and basketball (81.9%); and modest accuracy for dance (64.1%). The wrist model exhibited excellent classification accuracy for sitting (93.0%), standing (91.7%), and walking (95.8%); acceptable classification accuracy for basketball (86.0%); and modest accuracy for running (78.8%), lying down (74.6%) and dance (69.4%). Potential Impact Both the hip and wrist algorithms achieved acceptable classification accuracy, allowing researchers to use either placement for activity recognition.

Prediction of activity type in preschool children using machine learning techniques

Objectives Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. Design Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. Methods Eleven children aged 3–6 years (mean age = 4.8 ± 0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). Results Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. Conclusions Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.

The Catlin Seaview Survey – kilometre-scale seascape assessment, and monitoring of coral reef ecosystems

1.Marine ecosystems provide critically important goods and services to society, and hence their accelerated degradation underpins an urgent need to take rapid, ambitious and informed decisions regarding their conservation and management. 2.The capacity, however, to generate the detailed field data required to inform conservation planning at appropriate scales is limited by time and resource consuming methods for collecting and analysing field data at the large scales required. 3.The ‘Catlin Seaview Survey’, described here, introduces a novel framework for large-scale monitoring of coral reefs using high-definition underwater imagery collected using customized underwater vehicles in combination with computer vision and machine learning. This enables quantitative and geo-referenced outputs of coral reef features such as habitat types, benthic composition, and structural complexity (rugosity) to be generated across multiple kilometre-scale transects with a spatial resolution ranging from 2 to 6 m2. 4.The novel application of technology described here has enormous potential to contribute to our understanding of coral reefs and associated impacts by underpinning management decisions with kilometre-scale measurements of reef health. 5.Imagery datasets from an initial survey of 500 km of seascape are freely available through an online tool called the Catlin Global Reef Record. Outputs from the image analysis using the technologies described here will be updated on the online repository as work progresses on each dataset. 6.Case studies illustrate the utility of outputs as well as their potential to link to information from remote sensing. The potential implications of the innovative technologies on marine resource management and conservation are also discussed, along with the accuracy and efficiency of the methodologies deployed.

Assessing rod, cone and melanopsin contributions to human pupil flicker responses

Purpose: To determine the relative contributions of rods, cones and melanopsin to pupil responses in humans using temporal sinusoidal stimulation for light levels spanning the low mesopic to photopic range. Methods: A four-primary Ganzfeld photostimulator controlled flicker stimulations at seven light levels (-2.7 to 2 log cd/m2) and five frequencies (0.5 to 8Hz). Pupil diameter was measured using a high-resolution eyetracker. Three kinds of sinusoidal photoreceptor modulations were generated using silent substitution: 1) rod modulation, 2) cone modulation, and 3) combined rod and cone modulation in phase (Experiment 1) or phase shifted (Experiment 2) from a fixed rod phase. The melanopsin excitation was computed for each condition. A vector sum model was used to estimate the relative contribution of rods, cones and melanopsin to the pupil response. Results: From Experiment 1, the pupil frequency response peaked at 1Hz at two mesopic light levels for the three modulation conditions. Analyzing the rod-cone phase difference for the combined modulations (Experiment 2) identified a V-shaped response amplitude with a minimum between 135° and 180°. The pupil response phases increased as cone modulation phase increased. The pupil amplitude increased with increasing light level for cone and combined in-phase rod and cone modulation, but not for the rod modulation. Conclusions: These results demonstrate that cone- and rod-pathway contributions are more predominant than melanopsin contribution to the phasic pupil response. The combined rod, cone and melanopsin inputs to the phasic state of the pupil light reflex follow linear summation.

Natural convection due to differential heating of inclined walls and heat source placed on bottom wall of an attic shaped space

Numerical investigation of free convection heat transfer in an attic shaped enclosure with differentially heated two inclined walls and filled with air is performed in this study. The left inclined surface is uniformly heated whereas the right inclined surface is uniformly cooled. There is a heat source placed on the right side of the bottom surface. Rest of the bottom surface is kept as adiabatic. Finite volume based commercial software ANSYS 15 (Fluent) is used to solve the governing equations. Dependency of various flow parameters of fluid flow and heat transfer is analyzed including Rayleigh number, Ra ranging from 103 to 106, heater size from 0.2 to 0.6, heater position from 0.3 to 0.7 and aspect ratio from 0.2 to 1.0 with a fixed Prandtl number of 0.72. Outcomes have been reported in terms of temperature and stream function contours and local Nusselt number for various Ra, heater size, heater position, and aspect ratio. Grid sensitivity analysis is performed and numerically obtained results have been compared with those results available in the literature and found good agreement.

Human vs. machine : identification of bat species from their echolocation calls by humans and by artificial neural networks

Automated remote ultrasound detectors allow large amounts of data on bat presence and activity to be collected. Processing of such data involves identifying bat species from their echolocation calls. Automated species identification has the potential to provide more consistent, predictable, and potentially higher levels of accuracy than identification by humans. In contrast, identification by humans permits flexibility and intelligence in identification, as well as the incorporation of features and patterns that may be difficult to quantify. We compared humans with artificial neural networks (ANNs) in their ability to classify short recordings of bat echolocation calls of variable signal to noise ratios; these sequences are typical of those obtained from remote automated recording systems that are often used in large-scale ecological studies. We presented 45 recordings (1–4 calls) produced by known species of bats to ANNs and to 26 human participants with 1 month to 23 years of experience in acoustic identification of bats. Humans correctly classified 86% of recordings to genus and 56% to species; ANNs correctly identified 92% and 62%, respectively. There was no significant difference between the performance of ANNs and that of humans, but ANNs performed better than about 75% of humans. There was little relationship between the experience of the human participants and their classification rate. However, humans with <1 year of experience performed worse than others. Currently, identification of bat echolocation calls by humans is suitable for ecological research, after careful consideration of biases. However, improvements to ANNs and the data that they are trained on may in future increase their performance to beyond those demonstrated by humans.

Doubly Fed Induction Generators : Overview and Intelligent Control Strategies for Wind Energy Conversion Systems

Adjustable speed induction generators, especially the Doubly-Fed Induction Generators (DFIG) are becoming increasingly popular due to its various advantages over fixed speed generator systems. A DFIG in a wind turbine has ability to generate maximum power with varying rotational speed, ability to control active and reactive by integration of electronic power converters such as the back-to-back converter, low rotor power rating resulting in low cost converter components, etc, DFIG have become very popular in large wind power conversion systems. This chapter presents an extensive literature survey over the past 25 years on the different aspects of DFIG. Application of H8 Controller for enhanced DFIG-WT performance in terms of robust stability and reference tracking to reduce mechanical stress and vibrations is also demonstrated in the chapter.

Application of TS-Fuzzy Controller for Active Power and DC Capacitor Voltage Control in DFIG-Based Wind Energy Conversion Systems

This chapter focuses on the implementation of the TS (Tagaki-Sugino) fuzzy controller for the Doubly Fed Induction Generator (DFIG) based wind generator. The conventional PI control loops for mantaining desired active power and DC capacitor voltage is compared with the TS fuzzy controllers. DFIG system is represented by a third-order model where electromagnetic transients of the stator are neglected. The effectiveness of the TS-fuzzy controller on the rotor speed oscillations and the DC capacitor voltage variations of the DFIG damping controller on converter ratings is also investigated. The results from the time domain simulations are presented to elucidate the effectiveness of the TS-fuzzy controller over the conventional PI controller in the DFIG system. The proposed TS-fuzzy con-troller can improve the fault ride through capability of DFIG compared to the conventional PI controller.

Behavioral consistency, the homology assumption, and the problems of induction

The ultimate goal of profiling is to identify the major behavioral and personality characteristics to narrow the suspect pool. Inferences about offender characteristics can be accomplished deductively, based on the analysis of discrete offender behaviors established within a particular case. They can also be accomplished inductively, involving prediction based on abstract offender averages from group data (these methods and the logic on which they are based is detailed extensively in Chapters 2 and 4). As discussed, these two approaches are by no means equal.

Automatic UAV forced landing site detection using machine learning

The commercialization of aerial image processing is highly dependent on the platforms such as UAVs (Unmanned Aerial Vehicles). However, the lack of an automated UAV forced landing site detection system has been identified as one of the main impediments to allow UAV flight over populated areas in civilian airspace. This article proposes a UAV forced landing site detection system that is based on machine learning approaches including the Gaussian Mixture Model and the Support Vector Machine. A range of learning parameters are analysed including the number of Guassian mixtures, support vector kernels including linear, radial basis function Kernel (RBF) and polynormial kernel (poly), and the order of RBF kernel and polynormial kernel. Moreover, a modified footprint operator is employed during feature extraction to better describe the geometric characteristics of the local area surrounding a pixel. The performance of the presented system is compared to a baseline UAV forced landing site detection system which uses edge features and an Artificial Neural Network (ANN) region type classifier. Experiments conducted on aerial image datasets captured over typical urban environments reveal improved landing site detection can be achieved with an SVM classifier with an RBF kernel using a combination of colour and texture features. Compared to the baseline system, the proposed system provides significant improvement in term of the chance to detect a safe landing area, and the performance is more stable than the baseline in the presence of changes to the UAV altitude.

Improving robot vision models for object detection through interaction

We propose a method for learning specific object representations that can be applied (and reused) in visual detection and identification tasks. A machine learning technique called Cartesian Genetic Programming (CGP) is used to create these models based on a series of images. Our research investigates how manipulation actions might allow for the development of better visual models and therefore better robot vision. This paper describes how visual object representations can be learned and improved by performing object manipulation actions, such as, poke, push and pick-up with a humanoid robot. The improvement can be measured and allows for the robot to select and perform the `right' action, i.e. the action with the best possible improvement of the detector.

Teleoperation of a 7 DOF humanoid robot arm using human arm accelerations and EMG signals

We present our work on tele-operating a complex humanoid robot with the help of bio-signals collected from the operator. The frameworks (for robot vision, collision avoidance and machine learning), developed in our lab, allow for a safe interaction with the environment, when combined. This even works with noisy control signals, such as, the operator’s hand acceleration and their electromyography (EMG) signals. These bio-signals are used to execute equivalent actions (such as, reaching and grasping of objects) on the 7 DOF arm.

Numerical analysis for the time distributed-order and Riesz space fractional diffusions on bounded domains

Subdiffusion equations with distributed-order fractional derivatives describe some important physical phenomena. In this paper, we consider the time distributed-order and Riesz space fractional diffusions on bounded domains with Dirichlet boundary conditions. Here, the time derivative is defined as the distributed-order fractional derivative in the Caputo sense, and the space derivative is defined as the Riesz fractional derivative. First, we discretize the integral term in the time distributed-order and Riesz space fractional diffusions using numerical approximation. Then the given equation can be written as a multi-term time–space fractional diffusion. Secondly, we propose an implicit difference method for the multi-term time–space fractional diffusion. Thirdly, using mathematical induction, we prove the implicit difference method is unconditionally stable and convergent. Also, the solvability for our method is discussed. Finally, two numerical examples are given to show that the numerical results are in good agreement with our theoretical analysis.