Search

Following the success of Natural Language Processing (NLP) transformers pretrained via self-supervised learning, similar models have been proposed recently for speech processing such as Wav2Vec2, HuBERT and UniSpeech-SAT. An interesting yet unexplored area of application of these models is Spoken Dialogue Systems, where the users’ audio signals are typically just mapped to word-level features derived from an Automatic Speech Recogniser (ASR), and then processed using NLP techniques to generate system responses. This paper reports a comprehensive comparison of dialogue policies trained using ASR-based transcriptions and extended with the aforementioned audio processing transformers in the DSTC2 task. Whilst our dialogue policies are trained with supervised and policy-based deep reinforcement learning, they are assessed using both automatic task completion metrics and a human evaluation. Our results reveal that using audio embeddings is more beneficial than detrimental in most of our trained dialogue policies, and that the benefits are stronger for supervised learning than reinforcement learning.

Data augmentation can be a simple yet powerful tool for autonomous robots to fully utilise available data for self-supervised identification of atypical scenes or objects. State-of-the-art augmentation methods arbitrarily embed structural peculiarity in focal objects on typical images so that classifying these artefacts can provide guidance for learning representations for the detection of anomalous visual inputs. In this paper, however, we argue that learning such structure-sensitive representations can be a suboptimal approach to some classes of anomaly (e.g., unhealthy fruits) which are better recognised by a different type of visual element such as “colour”. We thus propose Channel Randomisation as a novel data augmentation method for restricting neural network models to learn encoding of “colour irregularity” whilst predicting channel-randomised images to ultimately build reliable fruit-monitoring robots identifying atypical fruit qualities. Our experiments show that (1) the colour-based alternative can better learn representations for consistently accurate identification of fruit anomalies in various fruit species, and (2) validation accuracy can be monitored for early stopping of training due to positive correlation between the colour-learning task and fruit anomaly detection. Moreover, the proposed approach is evaluated on a new anomaly dataset Riseholme-2021, consisting of 3:5K strawberry images collected from a mobile robot, which we share with the community to encourage active agri-robotics research.

In our previous work, we designed a systematic policy to prioritize sampling locations to lead significant accuracy improvement in spatial interpolation by using the prediction uncertainty of Gaussian Process Regression (GPR) as “attraction force” to deployed robots in path planning. Although the integration with Traveling Salesman Problem (TSP) solvers was also shown to produce relatively short travel distance, we here hypothesise several factors that could decrease the overall prediction precision as well because sub-optimal locations may eventually be included in their paths. To address this issue, in this paper, we first explore “local planning” approaches adopting various spatial ranges within which next sampling locations are prioritized to investigate their effects on the prediction performance as well as incurred travel distance. Also, Reinforcement Learning (RL)-based high-level controllers are trained to adaptively produce blended plans from a particular set of local planners to inherit unique strengths from that selection depending on latest prediction states. Our experiments on use cases of temperature monitoring robots demonstrate that the dynamic mixtures of planners can not only generate sophisticated, informative plans that a single planner could not create alone but also ensure significantly reduced travel distances at no cost of prediction reliability without any assist of additional modules for shortest path calculation.

Robots learning a new manipulation task from a small amount of demonstrations are increasingly demanded in different workspaces. A classifier model assessing the quality of actions can predict the successful completion of a task, which can be used by intelligent agents for action-selection. This paper presents a novel classifier that learns to classify task completion only from a few demonstrations. We carry out a comprehensive comparison of different neural classifiers, e.g. fully connected-based, fully convolutional-based, sequence2sequence-based, and domain adaptation-based classification. We also present a new dataset including five robot manipulation tasks, which is publicly available. We compared the performances of our novel classifier and the existing models using our dataset and the MIME dataset. The results suggest domain adaptation and timing-based features improve success prediction. Our novel model, i.e. fully convolutional neural network with domain adaptation and timing features, achieves an average classification accuracy of 97.3% and 95.5% across tasks in both datasets whereas state-of-the-art classifiers without domain adaptation and timing-features only achieve 82.4% and 90.3%, respectively.

Robots learning a new manipulation task from a small amount of demonstrations are increasingly demanded in different workspaces. A classifier model assessing the quality of actions can predict the successful completion of a task, which can be used by intelligent agents for action-selection. This paper presents a novel classifier that learns to classify task completion only from a few demonstrations. We carry out a comprehensive comparison of different neural classifiers, e.g. fully connected-based, fully convolutional-based, sequence2sequence-based, and domain adaptation-based classification. We also present a new dataset including five robot manipulation tasks, which is publicly available. We compared the performances of our novel classifier and the existing models using our dataset and the MIME dataset. The results suggest domain adaptation and timing-based features improve success prediction. Our novel model, i.e. fully convolutional neural network with domain adaptation and timing features, achieves an average classification accuracy of 97.3% and 95.5% across tasks in both datasets whereas state-of-the-art classifiers without domain adaptation and timing-features only achieve 82.4% and 90.3%, respectively.

A novel literature-based discovery system based on UMLS Ontologies, Semantic Filters, Statistics, and Word Embeddings was developed and validated against the well-established Raynaud’s disease – Fish Oil discovery by mining different size and specificity corpora of Pubmed titles and abstracts. Results show an ‘inverse effect’ between open versus closed discovery search modes. In open discovery, a more general and bigger corpus (Vascular disease or Perivascular disease) produces better results than a more specific and smaller in size corpus (Raynaud disease), whereas in closed discovery, the exact opposite is true.

A novel literature-based discovery system based on UMLS Ontologies, Semantic Filters, Statistics, and Word Embeddings was developed and validated against the well-established Raynaud’s disease – Fish Oil discovery by mining different size and specificity corpora of Pubmed titles and abstracts. Results show an ‘inverse effect’ between open versus closed discovery search modes. In open discovery, a more general and bigger corpus (Vascular disease or Perivascular disease) produces better results than a more specific and smaller in size corpus (Raynaud disease), whereas in closed discovery, the exact opposite is true.

In this paper, we propose a novel fall detection system based on a monocular camera. A single camera covering the living area is used for video recordings of an elderly person’s daily activities. From the video recordings, the human silhouette regions in every frame are extracted from the background, with related low-dimensionality representative features being automatically extracted by a convolutional neural network based autoencoder (CNN-AE). Extracted features together with the silhouette position information are combined together to construct an one class support vector machine (OCSVM) model for fall detection. From the comprehensive experimental evaluations in a real home environment,it is shown that the proposed fall detection method can detect different types of falls (falls in different orientations, falls with occlusions in a home environment) with high accuracy while achieving better performance than hand-crafted features based ones.

In recent years many deep neural networks have been proposed to solve Reading Comprehension (RC) tasks. Most of these models suffer from reasoning over long documents and do not trivially generalize to cases where the answer is not present as a span in a given document. We present a novel neural-based architecture that is capable of extracting relevant regions based on a given question-document pair and generating a well-formed answer. To show the effectiveness of our architecture, we conducted several experiments on the recently proposed and challenging RC dataset ‘NarrativeQA’. The proposed architecture outperforms state-of-the-art results (Tay et al., 2018) by 12.62% (ROUGE-L) relative improvement.

In recent years many deep neural networks have been proposed to solve Reading Comprehension (RC) tasks. Most of these models suffer from reasoning over long documents and do not trivially generalize to cases where the answer is not present as a span in a given document. We present a novel neural-based architecture that is capable of extracting relevant regions based on a given question-document pair and generating a well-formed answer. To show the effectiveness of our architecture, we conducted several experiments on the recently proposed and challenging RC dataset ‘NarrativeQA’. The proposed architecture outperforms state-of-the-art results (Tay et al., 2018) by 12.62% (ROUGE-L) relative improvement.

Purpose: In the United Kingdom (UK), the National Health Service (NHS) Diabetic Eye Screening Program o ers an annual eye examination to all people with diabetes aged 12 and over aimed at the early detection of people at high risk of visual loss due to diabetic retinopathy. The purpose of this study was to design a model for predicting patients at risk of developing retinopathy using patient characteristics and clinical measurements. Methods: We appraised data collected from the population-based Diabetic Eye Screening Program in East Anglia between 2011 and 2016. The data comprised reti- nal photographic screening results, patient characteristics of gender and age of the subject as well as duration and type of diabetes, and routine biochemical measures of Hemoglobin A1c (HbA1c), blood pressure, Albumin to Creatinine ratio (ACR), es- timated Glomerular Filtration rate (eGFR), serum creatinine, cholesterol, and Body Mass Index (BMI). Individuals were classified according to the presence or absence of retinopathy as indicated by their retinal photographic screening results. A logistic regression with Least Absolute Shrinkage and Selection Operator (lasso) regulariza- tion, random forest, gradient boosting machine, and regularized gradient boosting model were deployed and cross-validated for their predictive ability. Results: A total of 6375 subjects with recorded information for all available biochemical measures were identified from the cohorts. Of these, 5969 individuals had no signs of diabetic retinopathy. Of the remaining 406 individuals with signs of diabetic retinopathy, 352 had background diabetic retinopathy and 54 had referable diabetic retinopathy. The highest value of the ten-fold cross-validated area under the curve (AUC) of the receiver operating curve (ROC), 0.73 ± 0.03, was achieved by the gradient boosting machine and the minimum required set of variables to yield this perfor- mance included: duration of diabetes, HbA1c, ACR, and age. A subsequent anal

Movement Primitives (MP) are a well-established approach for representing modular and re-usable robot movement generators. Many state-of-the-art robot learning successes are based MPs, due to their compact representation of the inherently continuous and high dimensional robot movements. A major goal in robot learning is to combine multiple MPs as building blocks in a modular control architecture to solve complex tasks. To this effect, a MP representation has to allow for blending between motions, adapting to altered task variables, and co-activating multiple MPs in parallel. We present a probabilistic formulation of the MP concept that maintains a distribution over trajectories. Our probabilistic approach allows for the derivation of new operations which are essential for implementing all aforementioned properties in one framework. In order to use such a trajectory distribution for robot movement control, we analytically derive a stochastic feedback controller which reproduces the given trajectory distribution. We evaluate and compare our approach to existing methods on several simulated as well as real robot scenarios.

The determination of drug residence times, which define the time an inhibitor is in complex with its target, is a fundamental part of the drug discovery process. Synthesis and experimental measurements of kinetic rate constants are, however, expensive, and time-consuming. In this work, we aimed to obtain drug residence times computationally. Furthermore, we propose a novel algorithm to identify molecular design objectives based on ligand unbinding kinetics. We designed an enhanced sampling technique to accurately predict the free energy profiles of the ligand unbinding process, focusing on the free energy barrier for unbinding. Our method first identifies unbinding paths determining a corresponding set of internal coordinates (IC) that form contacts between the protein and the ligand, it then iteratively updates these interactions during a series of biased molecular-dynamics (MD) simulations to reveal the ICs that are important for the whole of the unbinding process. Subsequently, we performed finite temperature string simulations to obtain the free energy barrier for unbinding using the set of ICs as a complex reaction coordinate. Importantly, we also aimed to enable further design of drugs focusing on improved residence times. To this end, we developed a supervised machine learning (ML) approach with inputs from unbiased “downhill” trajectories initiated near the transition state (TS) ensemble of the string unbinding path. We demonstrate that our ML method can identify key ligand-protein interactions driving the system through the TS. Some of the most important drugs for cancer treatment are kinase inhibitors. One of these kinase targets is Cyclin Dependent Kinase 2 (CDK2), an appealing target for anticancer drug development. Here, we tested our method using two different CDK2 inhibitors for potential further development of these compounds. We compared the free energy barriers obtained from our calculations with those observed in available experimental data. We hi

Most deep-learning frameworks for understanding biological swarms are designed to fit perceptive models of group behavior to individual-level data (e.g., spatial coordinates of identified features of individuals) that have been separately gathered from video observations. Despite considerable advances in automated tracking, these methods are still very expensive or unreliable when tracking large numbers of animals simultaneously. Moreover, this approach assumes that the human-chosen features include sufficient features to explain important patterns in collective behavior. To address these issues, we propose training deep network models to predict system-level states directly from generic graphical features from the entire view, which can be relatively inexpensive to gather in a completely automated fashion. Because the resulting predictive models are not based on human-understood predictors, we use explanatory modules (e.g., Grad-CAM) that combine information hidden in the latent variables of the deep-network model with the video data itself to communicate to a human observer which aspects of observed individual behaviors are most informative in predicting group behavior. This represents an example of augmented intelligence in behavioral ecology—knowledge co-creation in a human–AI team. As proof of concept, we utilize a 20-day video recording of a colony of over 50 Harpegnathos saltator ants to showcase that, without any individual annotations provided, a trained model can generate an "importance map" across the video frames to highlight regions of important behaviors, such as dueling (which the AI has no a priori knowledge of), that play a role in the resolution of reproductive-hierarchy re-formation. Based on the empirical results, we also discuss the potential use and current challenges to further develop the proposed framework as a tool to discover behaviors that have not yet been considered crucial to understand complex social dynamics within biological collect

Deep reinforcement learning (DRL) is poised to revolutionise the field of artificial intelligence (AI) by endowing autonomous systems with high levels of understanding of the real world. Currently, deep learning (DL) is enabling DRL to effectively solve various intractable problems in various fields including computer vision, natural language processing, healthcare, robotics, to name a few. Most importantly, DRL algorithms are also being employed in audio signal processing to learn directly from speech, music and other sound signals in order to create audio-based autonomous systems that have many promising applications in the real world. In this article, we conduct a comprehensive survey on the progress of DRL in the audio domain by bringing together research studies across different but related areas in speech and music. We begin with an introduction to the general field of DL and reinforcement learning (RL), then progress to the main DRL methods and their applications in the audio domain. We conclude by presenting important challenges faced by audio-based DRL agents and by highlighting open areas for future research and investigation. The findings of this paper will guide researchers interested in DRL for the audio domain.

Neural Networks (NNs) are now being extensively utilised in various Artificial Intelligence platforms specifically in the area of image classification and real-time object tracking. We propose a novel design to address the problem of real time Unmanned Aerial Vehicle (UAV) monitoring and detection using a Zynq Ultrascale FPGA-based Convolutional Neural Network (CNN) implementation. The biggest challenge while implementing real-time algorithms on FPGAs is the limited DSP hardware resources available on FPGA platforms. Our proposed design overcomes the challenge of autonomous real time UAV detection and tracking on a Xilinx's Zynq Ultrascale XCZU9EG System on a Chip (SoC) platform. Our proposed design explores and provides a solution for overcoming the challenge of limited floating-point resources, whilst maintaining real-time performance. The solution consists of two modules: the UAV tracking and the neural network based UAV detection module. The tracking module uses our novel background-differencing algorithm whilst the UAV detection is based on a modified CNN algorithm, designed to give the maximum Field-Programmable Gate Array (FPGA) performance. These two modules are designed to complement each other and are enabled simultaneously to provide an enhanced real-time UAV detection for any given video input. The proposed system has been tested on detecting real-life flying UAVs, achieving an accuracy of 82\%, running at the full frame rate of the input camera for both tracking and Neural Network (NN) detection, achieving similar performance than an equivalent Deep Learning Processor Unit (DPU) Ultrascale FPGA based HD video and tracking implementation, but with lower resource utilisation as shown by our results.

In this work, we propose a framework for allowing autonomous robots deployed for extended periods of time in public spaces to adapt their own behaviour online from user interactions. The robot behaviour planning is embedded in a Reinforcement Learning (RL) framework, where the objective is maximising the level of overall user engagement during the interactions. We use the Upper-Confidence-Bound Value-Iteration (UCBVI) algorithm, which gives a helpful way of managing the exploration-exploitation trade-off for real-time interactions. An engagement model trained end-to-end generates the reward function in real-time during policy execution. We test this approach in a public museum in Lincoln (U.K.), where the robot is deployed as a tour guide for the visitors. Results show that after a couple of months of exploration, the robot policy learned to maintain the engagement of users for longer, with an increase of 22.8% over the initial static policy in the number of items visited during the tour and a 30% increase in the probability of completing the tour. This work is a promising step toward behavioural adaptation in long-term scenarios for robotics applications in social settings.

Quadratic time-frequency (TF) methods are commonly used for the analysis, modeling, and classification of time-varying non-stationary electroencephalogram (EEG) signals. Commonly employed TF methods suffer from an inherent tradeoff between cross-term suppression and preservation of auto-terms. In this paper, we propose a new convolutional neural network (CNN) based approach to enhancing TF images. The proposed method trains a CNN using the Wigner-Ville distribution as the input image and the ideal time-frequency distribution with the total concentration of signal energy along the IF curves as the output image. The results show significant improvement compared to the other state-of-the-art TF enhancement methods. The codes for reproducing the results can be accessed on the GitHub via https://github.com/nabeelalikhan1/CNN-based-TF-image-enhancement.

This work extends an existing virtual multi-agent platform called RoboSumo to create TripleSumo---a platform for investigating multi-agent cooperative behaviors in continuous action spaces, with physical contact in an adversarial environment. In this paper we investigate a scenario in which two agents, namely `Bug' and `Ant', must team up and push another agent `Spider' out of the arena. To tackle this goal, the newly added agent `Bug' is trained during an ongoing match between `Ant' and `Spider'. `Bug' must develop awareness of the other agents' actions, infer the strategy of both sides, and eventually learn an action policy to cooperate. The reinforcement learning algorithm Deep Deterministic Policy Gradient (DDPG) is implemented with a hybrid reward structure combining dense and sparse rewards. The cooperative behavior is quantitatively evaluated by the mean probability of winning the match and mean number of steps needed to win.

Classifiers trained on disjointed classes with few labelled data points are used in one-shot learning to identify visual concepts from other classes. Recently, Siamese networks and similarity layers have been used to solve the one-shot learning problem, achieving state-of-the-art performance on visual-character recognition datasets. Various techniques have been developed over the years to improve the performance of these networks on fine-grained image classification datasets. They focused primarily on improving the loss and activation functions, augmenting visual features, employing multiscale metric learning, and pre-training and fine-tuning the backbone network. We investigate similarity layers for one-shot learning tasks and propose two frameworks for combining these layers into a MergedNet network. On all four datasets used in our experiment, MergedNet outperformed the baselines based on classification accuracy, and it generalises to other datasets when trained on miniImageNet.

Since December 2019 the novel coronavirus SARS-CoV-2 has been identified as the cause of the pandemic COVID-19. Early symptoms overlap with other common conditions such as common cold and Influenza, making early screening and diagnosis are crucial goals for health practitioners. The aim of the study was to use machine learning (ML), an artificial neural network (ANN) and a simple statistical test to identify SARS-CoV-2 positive patients from full blood counts without knowledge of symptoms or history of the individuals. The dataset included in the analysis and training contains anonymized full blood counts results from patients seen at the Hospital Israelita Albert Einstein, at São Paulo, Brazil, and who had samples collected to perform the SARS-CoV-2 rt-PCR test during a visit to the hospital. Patient data was anonymised by the hospital, clinical data was standardized to have a mean of zero and a unit standard deviation. This data was made public with the aim to allow researchers to develop ways to enable the hospital to rapidly predict and potentially identify SARS-CoV-2 positive patients. We find that with full blood counts random forest, shallow learning and a flexible ANN model predict SARS-CoV-2 patients with high accuracy between populations on regular wards (AUC = 94–95%) and those not admitted to hospital or in the community (AUC = 80–86%). Here, AUC is the Area Under the receiver operating characteristics Curve and a measure for model performance. Moreover, a simple linear combination of 4 blood counts can be used to have an AUC of 85% for patients within the community. The normalised data of different blood parameters from SARS-CoV-2 positive patients exhibit a decrease in platelets, leukocytes, eosinophils, basophils and lymphocytes, and an increase in monocytes. SARS-CoV-2 positive patients exhibit a characteristic immune response profile pattern and changes in different parameters measured in the full blood count that are detected from simple and rapid

With the increasing popularity of social media andsmart devices, the face as one of the key biometrics becomesvital for person identification. Amongst those face recognitionalgorithms, video-based face recognition methods could make useof both temporal and spatial information just as humans do toachieve better classification performance. However, they cannotidentify individuals when certain key facial areas like eyes or noseare disguised by heavy makeup or rubber/digital masks. To thisend, we propose a novel deep spiking neural network architecturein this study. It takes dynamic facial movements, the facial musclechanges induced by speaking or other activities, as the sole input.An event-driven continuous spike-timing dependent plasticitylearning rule with adaptive thresholding is applied to train thesynaptic weights. The experiments on our proposed video-baseddisguise face database (MakeFace DB) demonstrate that theproposed learning method performs very well - it achieves from95% to 100% correct classification rates under various realisticexperimental scenarios

The paper presents a novel approach, based on deep learning, for diagnosis of Parkinson’s disease through medical imaging. The approach includes analysis and use of the knowledge extracted by Deep Convolutional and Recurrent Neural Networks (DNNs) when trained with medical images, such as Magnetic Resonance Images and DaTscans. Internal representations of the trained DNNs constitute the extracted knowledge which is used in a transfer learning and domain adaptation manner, so as to create a unified framework for prediction of Parkinson’s across different medical environments. A large experimental study is presented illustrating the ability of the proposed approach to effectively predict Parkinson’s, using different medical image sets from real environments.

With Europe’s ageing fleet of nuclear reactors operating closer to their safety limits, the monitoring of such reactors through complex models has become of great interest to maintain a high level of availability and safety. Therefore, we propose an extended Deep Learning framework as part of the CORTEX Horizon 2020 EU project for the unfolding of reactor transfer functions from induced neutron noise sources. The unfolding allows for the identification and localisation of reactor core perturbation sources from neutron detector readings in Pressurised Water Reactors. A 3D Convolutional Neural Network (3D-CNN) and Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) have been presented, each to study the signals presented in frequency and time domain respectively. The proposed approach achieves state-of-the-art results with the classification of perturbation type in the frequency domain reaching 99.89% accuracy and localisation of the classified perturbation source being regressed to 0.2902 Mean Absolute Error (MAE).

In this paper, a marker-based, single-person optical motion capture method (DeepMoCap) is proposed using multiple spatio-temporally aligned infrared-depth sensors and retro-reflective straps and patches (reflectors). DeepMoCap explores motion capture by automatically localizing and labeling reflectors on depth images and, subsequently, on 3D space. Introducing a non-parametric representation to encode the temporal correlation among pairs of colorized depthmaps and 3D optical flow frames, a multi-stage Fully Convolutional Network (FCN) architecture is proposed to jointly learn reflector locations and their temporal dependency among sequential frames. The extracted reflector 2D locations are spatially mapped in 3D space, resulting in robust 3D optical data extraction. The subject’s motion is efficiently captured by applying a template-based fitting technique on the extracted optical data. Two datasets have been created and made publicly available for evaluation purposes; one comprising multi-view depth and 3D optical flow annotated images (DMC2.5D), and a second, consisting of spatio-temporally aligned multi-view depth images along with skeleton, inertial and ground truth MoCap data (DMC3D). The FCN model outperforms its competitors on the DMC2.5D dataset using 2D Percentage of Correct Keypoints (PCK) metric, while the motion capture outcome is evaluated against RGB-D and inertial data fusion approaches on DMC3D, outperforming the next best method by 4.5% in total 3D PCK accuracy.

—We develop a novel machine learning based robotic strawberry harvesting system for fruit counting, sizing/weighting, and yield prediction.

Non-intrusive load monitoring (NILM) is the process in which a household’s total power consumption is used to determine the power consumption of household appliances. Previous work has shown that sequence-to-point (seq2point) learning is one of the most promising methods for tackling NILM. This process uses a sequence of aggregate power data to map a target appliance's power consumption at the midpoint of that window of power data. However, models produced using this method contain upwards of thirty million weights, meaning that the models require large volumes of resources to perform disaggregation. This paper addresses this problem by pruning the weights learned by such a model, which results in a lightweight NILM algorithm for the purpose of being deployed on mobile devices such as smart meters. The pruned seq2point learning algorithm was applied to the REFIT data, experimentally showing that the performance was retained comparing to the original seq2point learning whilst the number of weights was reduced by 87\%. Code:https://github.com/JackBarber98/pruned-nilm

Parkinsons disease (PD) can affect a person’s gait and potentially lead to some gait impairments (e.g., freezing gait, shuffling gait,etc.) for a PD patient. Analyzing a person’s gait characteristics is important for both the early diagnosis and evaluation of their PD. In this work, a novel computer vision based technique is proposed for gait analysis to classify normal or Parkinson’s gaits, by using a normal RGB camera. Based on recorded videos of normal gaits, a mask R-CNN, which is a modern deep neural network for objects segmentation, is applied for extracting human silhouettes from video frames. Gait energy images (GEIs) are then obtained from human silhouettes extracted from video clips of normal gaits and processed as features, which are applied to construct a one class support vector machine (OCSVM) model for normal/PD gaits classification. Comprehensive experimental studies show that the proposed technique can successfully classify normal/PD gaits with a high accuracy of more than 97%.

Since the emergence of contemporary area classifications, population geography has witnessed a renaissance in the area of policy related spatial analysis. Area classifications subsume geodemographic systems which often use data mining techniques and machine learning algorithms to simplify large and complex bodies of information about people and the places in which they live, work and undertake other social activities. Outputs developed from the grouping of small geographical areas on the basis of multi- dimensional data have proved beneficial particularly for decision-making in the commercial sectors of a vast number of countries in the northern hemisphere. This book argues that small area classifications offer countries in the Global South a distinct opportunity to address human population policy related challenges in novel ways using area-based initiatives and evidence-based methods.

The global pandemic of coronavirus disease 2019 (COVID-19) is continuing to have a significant effect on the well-being of the global population, thus increasing the demand for rapid testing, diagnosis, and treatment. As COVID-19 can cause severe pneumonia, early diagnosis is essential for correct treatment, as well as to reduce the stress on the healthcare system. Along with COVID-19, other etiologies of pneumonia and Tuberculosis (TB) constitute additional challenges to the medical system. Pneumonia (viral as well as bacterial) kills about 2 million infants every year and is consistently estimated as one of the most important factor of childhood mortality (according to the World Health Organization). Chest X-ray (CXR) and computed tomography (CT) scans are the primary imaging modalities for diagnosing respiratory diseases. Although CT scans are the gold standard, they are more expensive, time consuming, and are associated with a small but significant dose of radiation. Hence, CXR have become more widespread as a first line investigation. In this regard, the objective of this work is to develop a new deep transfer learning pipeline, named DenResCov-19, to diagnose patients with COVID-19, pneumonia, TB or healthy based on CXR images. The pipeline consists of the existing DenseNet-121 and the ResNet-50 networks. Since the DenseNet and ResNet have orthogonal performances in some instances, in the proposed model we have created an extra layer with convolutional neural network (CNN) blocks to join these two models together to establish superior performance as compared to the two individual networks. This strategy can be applied universally in cases where two competing networks are observed. We have tested the performance of our proposed network on two-class (pneumonia and healthy), three-class (COVID-19 positive, healthy, and pneumonia), as well as four-class (COVID-19 positive, healthy, TB, and pneumonia) classification problems. We have validated that our proposed net

Vaccine hesitancy is an ongoing concern, presenting a major threat to global health. SARS-CoV-2 COVID-19 vaccinations are no exception as misinformation began to circulate on social media early in their development. Twitter’s Application Programming Interface (API) for Python was used to collect 137,781 tweets between 1 July 2021 and 21 July 2021 using 43 search terms relating to COVID-19 vaccines. Tweets were analysed for sentiment using Microsoft Azure (a machine learning approach) and the VADER sentiment analysis model (a lexicon-based approach), where the Natural Language Processing Toolkit (NLTK) assessed whether tweets represented positive, negative or neutral opinions. The majority of tweets were found to be negative in sentiment (53,899), followed by positive (53,071) and neutral (30,811). The negative tweets displayed a higher intensity of sentiment than positive tweets. A questionnaire was distributed and analysis found that individuals with full vaccination histories were less concerned about receiving and were more likely to accept the vaccine. Overall, we determined that this sentiment-based approach is useful to establish levels of vaccine hesitancy in the general public and, alongside the questionnaire, suggests strategies to combat specific concerns and misinformation.

The analysis of retinal Spectral-Domain Optical Coherence Tomography (SD-OCT) images by trained medical professionals can be used to provide useful insights into various diseases. It is the most popular method of retinal imaging due to its non-invasive nature and the useful information it provides for making an accurate diagnosis. A deep learning approach for automating the segmentation of Cystoid Macular Edema (fluid) in retinal OCT B-Scan images was developed that is consequently used for volumetric analysis of OCT scans. This solution is a fast and accurate semantic segmentation network that makes use of a shortened encoder-decoder UNet like architecture with an integrated Dense ASPP module and Attention Gate for producing an accurate and refined retinal fluid segmentation map. Our system was evaluated against both publicly and privately available datasets; on the former the network achieved a Dice coefficient of 0.804, thus making it the current best performing approach on this dataset, and on the very small and challenging private dataset, it achieved a score of 0.691. Due to the lack of publicly available data in this domain, a Graphical User Interface that aims to semi-automate the labelling process of OCT images was also created, thus greatly simplifying the process of the dataset creation and potentially leading to an increase in labelled data production.

OBJECTIVES: Childhood blindness from retinopathy of prematurity (ROP) is increasing as a result of improvements in neonatal care worldwide. We evaluate the effectiveness of artificial intelligence (AI)–based screening in an Indian ROP telemedicine program and whether differences in ROP severity between neonatal care units (NCUs) identified by using AI are related to differences in oxygen-titrating capability. METHODS: External validation study of an existing AI-based quantitative severity scale for ROP on a data set of images from the Retinopathy of Prematurity Eradication Save Our Sight ROP telemedicine program in India. All images were assigned an ROP severity score (1–9) by using the Imaging and Informatics in Retinopathy of Prematurity Deep Learning system. We calculated the area under the receiver operating characteristic curve and sensitivity and specificity for treatment-requiring retinopathy of prematurity. Using multivariable linear regression, we evaluated the mean and median ROP severity in each NCU as a function of mean birth weight, gestational age, and the presence of oxygen blenders and pulse oxygenation monitors. RESULTS: The area under the receiver operating characteristic curve for detection of treatment requiring retinopathy of prematurity was 0.98, with 100% sensitivity and 78% specificity. We found higher median (interquartile range) ROP severity in NCUs without oxygen blenders and pulse oxygenation monitors, most apparent in bigger infants (.1500 g and 31 weeks’ gestation: 2.7 [2.5–3.0] vs 3.1 [2.4–3.8]; P = .007, with adjustment for birth weight and gestational age). CONCLUSIONS: Integration of AI into ROP screening programs may lead to improved access to care for secondary prevention of ROP and may facilitate assessment of disease epidemiology and NCU resources.

This paper presents the results of experimentation in computer vision based for the perception of the artist drawing with analog media (pen and paper), with the aim to contribute towards a human- robot co-creative drawing framework. Using data gathered from user studies with artists and illustrators, two types of CNN models were de- signed and evaluated to predict an artist’s activity (e.g. are they drawing or not?) and the position of the pen on the canvas based only on a multi- camera input of the drawing surface. Results of different combination of input sources are presented, with an overall mean accuracy of 95% (std: 7%) for predicting when the artist is present and 68% (std: 15%) for predicting when the artist is drawing; and mean squared normalised error of 0.0034 (std: 0.0099) of predicting the pen’s position on the drawing canvas. These results point toward an autonomous robotic system having an awareness of an artist at work via camera based input and contributes toward the development of a more fluid physical to digital workflow for creative content creation.

Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the reward learning process so that new skills can be taught to robots by their users. To address such automation, we consider task success classifiers using visual observations to estimate the rewards in terms of task success. In this work, we study the performance of multiple state-of-the-art deep reinforcement learning algorithms under different types of reward: Dense, Sparse, Visual Dense, and Visual Sparse rewards. Our experiments in various simulation tasks (Pendulum, Reacher, Pusher, and Fetch Reach) show that while DRL agents can learn successful behaviours using visual rewards when the goal targets are distinguishable, their performance may decrease if the task goal is not clearly visible. Our results also show that visual dense rewards are more successful than visual sparse rewards and that there is no single best algorithm for all tasks.

Congenital fibrosis of the extraocular muscles (CFEOM) is a congenital cranial dysinnervation disorder caused by developmental abnormalities affecting cranial nerves/nuclei innervating the extraocular muscles. Autosomal dominant CFEOM arises from heterozygous missense mutations of KIF21A or TUBB3. Although spatiotemporal expression studies have shown KIF21A and TUBB3 expression in developing retinal ganglion cells, it is unclear whether dysinnervation extends beyond the oculomotor system. We aimed to investigate whether dysinnervation extends to the visual system by performing high-resolution optical coherence tomography (OCT) scans characterizing retinal ganglion cells within the optic nerve head and retina. Sixteen patients with CFEOM were screened for mutations in KIF21A, TUBB3, and TUBB2B. Six patients had apparent optic nerve hypoplasia. OCT showed neuro-retinal rim loss. Disc diameter, rim width, rim area, and peripapillary nerve fiber layer thickness were significantly reduced in CFEOM patients compared to controls (p < 0.005). Situs inversus of retinal vessels was seen in five patients. Our study provides evidence of structural optic nerve and retinal changes in CFEOM. We show for the first time that there are widespread retinal changes beyond the retinal ganglion cells in patients with CFEOM. This study shows that the phenotype in CFEOM extends beyond the motor nerves.

In our previous work, we designed a systematic policy to prioritize sampling locations to lead significant accuracy improvement in spatial interpolation by using the prediction uncertainty of Gaussian Process Regression (GPR) as “attraction force” to deployed robots in path planning. Although the integration with Traveling Salesman Problem (TSP) solvers was also shown to produce relatively short travel distance, we here hypothesise several factors that could decrease the overall prediction precision as well because sub-optimal locations may eventually be included in their paths. To address this issue, in this paper, we first explore “local planning” approaches adopting various spatial ranges within which next sampling locations are prioritized to investigate their effects on the prediction performance as well as incurred travel distance. Also, Reinforcement Learning (RL)-based high-level controllers are trained to adaptively produce blended plans from a particular set of local planners to inherit unique strengths from that selection depending on latest prediction states. Our experiments on use cases of temperature monitoring robots demonstrate that the dynamic mixtures of planners can not only generate sophisticated, informative plans that a single planner could not create alone but also ensure significantly reduced travel distances at no cost of prediction reliability without any assist of additional modules for shortest path calculation.

Biology is both an important application area and a source of motivation for development of advanced machine learning techniques. Although much attention has been paid to large and complex data sets resulting from high-throughput sequencing, advances in high-quality video recording technology have begun to generate similarly rich data sets requiring sophisticated techniques from both computer vision and time-series analysis. Moreover, just as studying gene expression patterns in one organism can reveal general principles that apply to other organisms, the study of complex social interactions in an experimentally tractable model system, such as a laboratory ant colony, can provide general principles about the dynamics of other social groups. Here, we focus on one such example from the study of reproductive regulation in small laboratory colonies of more than 50 Harpegnathos ants. These ants can be artificially induced to begin a ~20 day process of hierarchy reformation. Although the conclusion of this process is conspicuous to a human observer, it remains unclear which behaviors during the transient period are contributing to the process. To address this issue, we explore the potential application of One-class Classification (OC) to the detection of abnormal states in ant colonies for which behavioral data is only available for the normal societal conditions during training. Specifically, we build upon the Deep Support Vector Data Description (DSVDD) and introduce the Inner-Outlier Generator (IO-GEN) that synthesizes fake “inner outlier” observations during training that are near the center of the DSVDD data description.We show that IO-GEN increases the reliability of the final OC classifier relative to other DSVDD baselines. This method can be used to screen video frames for which additional human observation is needed. Although we focus on an application with laboratory colonies of social insects, this approach may be applied to video data from other social systems

This paper explores the application of unsupervised learning to detecting anomalies in mouse video data. The two models presented in this paper are a dual stream, 3D convolutional autoencoder (with residual connections) and a dual stream, 2D convolutional autoencoder. The publicly available dataset used here contains twelve videos of a single home-caged mice alongside frame level annotations. Under the pretext that the autoencoder only sees normal events, the video data was handcrafted to treat each behaviour as a pseudo-anomaly thereby eliminating them from the others during training. The results are presented for one conspicuous behaviour (hang) and one inconspicuous behaviour (groom). The performance of these models is compared to a single stream autoencoder and a supervised learning model, which are both based on the custom CAE encoder. Both models are also tested on the CUHK Avenue dataset were found to perform as well as some state-of-the-art architectures.

As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. This work provides an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms developed to tackle the problem; and advice on effective tools and implementation. We intend this paper to serve two audiences. First, we want to familiarize machine learning experts with the challenges of imitation learning, particularly those arising in robotics, and the interesting theoretical and practical distinctions between it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. Second, we want to give roboticists and experts in applied artificial intelligence a broader appreciation for the frameworks and tools available for imitation learning. We pay particular attention to the intimate connection between imitation learning approaches and those of structured prediction Daumé III et al. [2009]. To structure this discussion, we categorize imitation learning techniques based on the following key criteria which drive algorithmic decisions: 1) The structure of the policy space. Is the learned policy a time-index trajectory (trajectory learning), a mapping from observations to actions (so called behavioral cloning [Bain and Sammut, 1996]), or the result of a complex optimization or planning problem at each execution as is common in inverse optimal control methods [Kalman, 1964, Moylan and Anderson, 1973]. 2) The information available during training and testing. In particular, is the learning algorithm privy to the full state that the t

Plant phenotyping is an essential step in the plant breeding cycle, necessary to ensure food safety for a growing world population. Standard procedures for evaluating three-dimensional plant morphology and extracting relevant phenotypic characteristics are slow, costly, and in need of automation. Previous work towards automatic semantic segmentation of plants relies on explicit prior knowledge about the species and sensor set-up, as well as manually tuned parameters. In this work, we propose to use a supervised machine learning algorithm to predict per-point semantic annotations directly from point cloud data of whole plants and minimise the necessary user input. We train a PointNet++ variant on a fully annotated procedurally generated data set of partial point clouds of tomato plants, and show that the network is capable of distinguishing between the semantic classes of leaves, stems, and soil based on structural data only. We present both quantitative and qualitative evaluation results, and establish a proof of concept, indicating that deep learning is a promising approach towards replacing the current complex, laborious, species-specific, state-of-the-art plant segmentation procedures.

Movement Primitives (MP) are a well-established approach for representing modular and re-usable robot movement generators. Many state-of-the-art robot learning successes are based MPs, due to their compact representation of the inherently continuous and high dimensional robot movements. A major goal in robot learning is to combine multiple MPs as building blocks in a modular control architecture to solve complex tasks. To this effect, a MP representation has to allow for blending between motions, adapting to altered task variables, and co-activating multiple MPs in parallel. We present a probabilistic formulation of the MP concept that maintains a distribution over trajectories. Our probabilistic approach allows for the derivation of new operations which are essential for implementing all aforementioned properties in one framework. In order to use such a trajectory distribution for robot movement control, we analytically derive a stochastic feedback controller which reproduces the given trajectory distribution. We evaluate and compare our approach to existing methods on several simulated as well as real robot scenarios.

The autonomous landing of an Unmanned Aerial Vehicle (UAV) on a marker is one of the most challenging problems in robotics. Many solutions have been proposed, with the best results achieved via customized geometric features and external sensors. This paper discusses for the first time the use of deep reinforcement learning as an end-to-end learning paradigm to find a policy for UAVs autonomous landing. Our method is based on a divide-and-conquer paradigm that splits a task into sequential sub-tasks, each one assigned to a Deep Q-Network (DQN), hence the name Sequential Deep Q-Network (SDQN). Each DQN in an SDQN is activated by an internal trigger, and it represents a component of a high-level control policy, which can navigate the UAV towards the marker. Different technical solutions have been implemented, for example combining vanilla and double DQNs, and the introduction of a partitioned buffer replay to address the problem of sample efficiency. One of the main contributions of this work consists in showing how an SDQN trained in a simulator via domain randomization, can effectively generalize to real-world scenarios of increasing complexity. The performance of SDQNs is comparable with a state-of-the-art algorithm and human pilots while being quantitatively better in noisy conditions.

In this paper, we present an algorithm to identify different types of objects from 2D and 3D laser range data. Our method is a combination of an instance-based feature extraction similar to the Nearest-Neighbor classifier (NN) and a collective classification method that utilizes associative Markov networks (AMNs). Compared to previous approaches, we transform the feature vectors so that they are better separable by linear hyperplanes, which are learned by the AMN classifier. We present results of extensive experiments in which we evaluate the performance of our algorithm on several recorded indoor scenes and compare it to the standard AMN approach as well as the NN classifier. The classification rate obtained with our algorithm substantially exceeds those of the AMN and the NN.

New understanding of the brain function and increasing availability of low-cost-non-invasive electroencephalograms (EEGs) recording devices have made brain-computer-interface (BCI) as an alternative option to augmentation of human capabilities by providing a new non-muscular channel for sending commands, which could be used to activate electronic or mechanical devices based on modulation of thoughts. In this project, our emphasis will be on how to develop such a BCI using fuzzy rule-based systems (FRBSs), metaheuristics and Neural Mass Models (NMMs). In particular, we treat the BCI system as an integrated problem consisting of mathematical modelling, machine learning and classification. Four main steps are involved in designing a BCI system: 1) data acquisition, 2) feature extraction, 3) classification and 4) transferring the classification outcome into control commands for extended peripheral capability. Our focus has been placed on the first three steps. This research project aims to investigate and develop a novel BCI framework encompassing classification based on machine learning, optimisation and neural mass modelling. The primary aim in this project is to bridge the gap of these three different areas in a bid to design a more reliable and accurate communication path between the brain and external world. To achieve this goal, the following objectives have been investigated: 1) Steady-State Visual Evoked Potential (SSVEP) EEG data are collected from human subjects and pre-processed; 2) Feature extraction procedure is implemented to detect and quantify the characteristics of brain activities which indicates the intention of the subject.; 3) a classification mechanism called an Immune Inspired Multi-Objective Fuzzy Modelling Classification algorithm (IMOFM-C), is adapted as a binary classification approach for classifying binary EEG data. Then, the DDAG-Distance aggregation approach is proposed to aggregate the outcomes of IMOFM-C based binary classifiers for mult

Automated diagnosis of covid19 in chest CTs is becoming a clinically important technique to support precision and efficient diagnosis and treatment planning. A few efforts have been made to automatically diagnose the COVID-19 in CTs using CNNs, and the task still remains a challenge. In this paper, we present a transformer-based framework for COVID19 classification. We attempt to expand the adaption of vision transformer as a robust feature learner to the 3D CTs to diagnose the COVID-19. The framework consists of two main stages: lung segmentation using UNet followed by the classification, in which the features extracted from each CT slice using Swin transformer in a CT scan are aggregated into 3D volume level feature. We also investigated the performance of using the robust CNNs (BiT and EfficientNetV2) as backbones in the framework. The dataset from the ICCV workshop: MIA-COV19D, is used in our experiments. The evaluation results show that the method with the backbone of Swin transformer gain the best F1 score of 0.935 on the validation dataset, while the CNN based backbone of EfficientNetV2 has the competitive classification performance with the best precision of 93.7%. The final prediction model with Swin transformer achieves the F1 score of 0.84 on the test dataset, which doesn't require an additional post-processing stage.

Marker-less motion capture is a rapidly advancing field that can take simple RGB image sequences, or more advanced Red Green Blue Depth (RGB-D) image sequences obtained using depth sensors, and outputs an estimated human pose. This method of human pose estimation allows for the extraction of biomechanical features which can then be analysed by clinicians to give more insights into a patient’s movement capabilities. When compared to other, more clinically proven technologies such as the Knee Kinesiography (KneeKG), biomechanics presented have the advantage of being more representative of natural movement without the obstructive markers placed on the body. This Significant difference of up to 10 degrees in a range of motion for the knee could be the key to better identifying a person’s gait or tracking their natural walking pattern over time, while also being more robust and better suited to a smaller clinical environment.

Automated diagnosis of covid19 in chest CTs is becoming a clinically important technique to support precision and efficient diagnosis and treatment planning. A few efforts have been made to automatically diagnose the COVID-19 in CTs using CNNs, and the task still remains a challenge. In this paper, we present a transformer-based framework for COVID19 classification. We attempt to expand the adaption of vision transformer as a robust feature learner to the 3D CTs to diagnose the COVID-19. The framework consists of two main stages: lung segmentation using UNet followed by the classification, in which the features extracted from each CT slice using Swin transformer in a CT scan are aggregated into 3D volume level feature. We also investigated the performance of using the robust CNNs (BiT and EfficientNetV2) as backbones in the framework. The dataset from the ICCV workshop: MIA-COV19D, is used in our experiments. The evaluation results show that the method with the backbone of Swin transformer gain the best F1 score of 0.935 on the validation dataset, while the CNN based backbone of EfficientNetV2 has the competitive classification performance with the best precision of 93.7%. The final prediction model with Swin transformer achieves the F1 score of 0.84 on the test dataset, which doesn't require an additional post-processing stage.

Tea chrysanthemum detection at its flowering stage is one of the key components for selective chrysanthemum harvesting robot development. However, it is a challenge to detect flowering chrysanthemums under unstructured field environments given variations on illumination, occlusion and object scale. In this context, we propose a highly fused and lightweight deep learning architecture based on YOLO for tea chrysanthemum detection (TC-YOLO). First, in the backbone component and neck component, the method uses the Cross-Stage Partially Dense network (CSPDenseNet) and the Cross-Stage Partial ResNeXt network (CSPResNeXt) as the main networks, respectively, and embeds custom feature fusion modules to guide the gradient flow. In the final head component, the method combines the recursive feature pyramid (RFP) multiscale fusion reflow structure and the Atrous Spatial Pyramid Pool (ASPP) module with cavity convolution to achieve the detection task. The resulting model was tested on 300 field images using a data enhancement strategy combining flipping and rotation, showing that under the NVIDIA Tesla P100 GPU environment, if the inference speed is 47.23 FPS for each image (416 × 416), TC-YOLO can achieve the average precision (AP) of 92.49% on our own tea chrysanthemum dataset. Through further validation, it was found that overlap had the least effect on tea chrysanthemum detection, and illumination had the greatest effect on tea chrysanthemum detection. In addition, this method (13.6 M) can be deployed on a single mobile GPU, and it could be further developed as a perception system for a selective chrysanthemum harvesting robot in the future.

Digital Twin (DT) is an emerging technology that is a cornerstone of the 4 th industrial revolution. Over the next decade, it is expected to revolutionise industrial processes via Internet of Things (IoT) and other enabling technologies such as 5G for better performance and safety. DT as a real time virtual representation of any physical system is envisaged to ensure better connectivity of industrial processes, increased speed of decision making and effective prediction that could lead to optimised performance enhancement at various levels in the business chain. However, unsecured, or poorly secured DTs can cause serious harm to an enterprise in key industrial sectors such as manufacturing and oil and gas which are of utmost importance to the world’s economy. The focus of this paper, therefore, is to identify security vulnerabilities of DTs in applied to the oil and gas industry and analyse effective security frameworks for monitoring oil and gas pipeline data and its transmission over various networks including through the Cloud. This is to prevent man-in-the-middle-attacks and reduce economic losses that can result. Furthermore, important considerations on the data attributes will be explored. These include accuracy of the data transmitted under various security implementation regimes, its completeness, and transmission delay of the various frameworks.