Hardware Efficient Direct Policy Imitation Learning for Robotic Navigation in Resource-Constrained Settings.

Direct policy learning (DPL) is a widely used approach in imitation learning for time-efficient and effective convergence when training mobile robots. However, using DPL in real-world applications is not sufficiently explored due to the inherent challenges of mobilizing direct human expertise and the difficulty of measuring comparative performance. Furthermore, autonomous systems are often resource-constrained, thereby limiting the potential application and implementation of highly effective deep learning models. In this work, we present a lightweight DPL-based approach to train mobile robots in navigational tasks. We integrated a safety policy alongside the navigational policy to safeguard the robot and the environment. The approach was evaluated in simulations and real-world settings and compared with recent work in this space. The results of these experiments and the efficient transfer from simulations to real-world settings demonstrate that our approach has improved performance compared to its hardware-intensive counterparts. We show that using the proposed methodology, the training agent achieves closer performance to the expert within the first 15 training iterations in simulation and real-world settings.

Habitual Physical Activity of People with or at Risk of Diabetes-Related Foot Complications.

Regular physical activity is an important component of diabetes management. However, there are limited data on the habitual physical activity of people with or at risk of diabetes-related foot complications. The aim of this study was to describe the habitual physical activity of people with or at risk of diabetes-related foot complications in regional Australia. Twenty-three participants with diabetes from regional Australia were recruited with twenty-two participants included in subsequent analyses: no history of ulcer (N = 11) and history of ulcer (N = 11). Each participant wore a triaxial accelerometer (GT3X+; ActiGraph LLC, Pensacola, FL, USA) on their non-dominant wrist for 14 days. There were no significant differences between groups according to both participant characteristics and physical activity outcomes. Median minutes per day of moderate-to-vigorous physical activity (MVPA) were 9.7 (IQR: 1.6-15.7) while participants recorded an average of 280 ± 78 min of low-intensity physical activity and 689 ± 114 min of sedentary behaviour. The sample accumulated on average 30 min of slow walking and 2 min of fast walking per day, respectively. Overall, participants spent very little time performing MVPA and were largely sedentary. It is important that strategies are put in place for people with or at risk of diabetes-related foot complications in order that they increase their physical activity significantly in accordance with established guidelines.

A Mental Health Chatbot with Cognitive Skills for Personalised Behavioural Activation and Remote Health Monitoring.

Mental health issues are at the forefront of healthcare challenges facing contemporary human society. These issues are most prevalent among working-age people, impacting negatively on the individual, his/her family, workplace, community, and the economy. Conventional mental healthcare services, although highly effective, cannot be scaled up to address the increasing demand from affected individuals, as evidenced in the first two years of the COVID-19 pandemic. Conversational agents, or chatbots, are a recent technological innovation that has been successfully adapted for mental healthcare as a scalable platform of cross-platform smartphone applications that provides first-level support for such individuals. Despite this disposition, mental health chatbots in the extant literature and practice are limited in terms of the therapy provided and the level of personalisation. For instance, most chatbots extend Cognitive Behavioural Therapy (CBT) into predefined conversational pathways that are generic and ineffective in recurrent use. In this paper, we postulate that Behavioural Activation (BA) therapy and Artificial Intelligence (AI) are more effectively materialised in a chatbot setting to provide recurrent emotional support, personalised assistance, and remote mental health monitoring. We present the design and development of our BA-based AI chatbot, followed by its participatory evaluation in a pilot study setting that confirmed its effectiveness in providing support for individuals with mental health issues.

A Robust Artificial Intelligence Approach with Explainability for Measurement and Verification of Energy Efficient Infrastructure for Net Zero Carbon Emissions.

Rapid urbanization across the world has led to an exponential increase in demand for utilities, electricity, gas and water. The building infrastructure sector is one of the largest global consumers of electricity and thereby one of the largest emitters of greenhouse gas emissions. Reducing building energy consumption directly contributes to achieving energy sustainability, emissions reduction, and addressing the challenges of a warming planet, while also supporting the rapid urbanization of human society. Energy Conservation Measures (ECM) that are digitalized using advanced sensor technologies are a formal approach that is widely adopted to reduce the energy consumption of building infrastructure. Measurement and Verification (M&V) protocols are a repeatable and transparent methodology to evaluate and formally report on energy savings. As savings cannot be directly measured, they are determined by comparing pre-retrofit and post-retrofit usage of an ECM initiative. Given the computational nature of M&V, artificial intelligence (AI) algorithms can be leveraged to improve the accuracy, efficiency, and consistency of M&V protocols. However, AI has been limited to a singular performance metric based on default parameters in recent M&V research. In this paper, we address this gap by proposing a comprehensive AI approach for M&V protocols in energy-efficient infrastructure. The novelty of the framework lies in its use of all relevant data (pre and post-ECM) to build robust and explainable predictive AI models for energy savings estimation. The framework was implemented and evaluated in a multi-campus tertiary education institution setting, comprising 200 buildings of diverse sensor technologies and operational functions. The results of this empirical evaluation confirm the validity and contribution of the proposed framework for robust and explainable M&V for energy-efficient building infrastructure and net zero carbon emissions.

Cancer in Lockdown: Impact of the COVID-19 Pandemic on Patients with Cancer.

The lockdown measures of the ongoing COVID-19 pandemic have disengaged patients with cancer from formal health care settings, leading to an increased use of social media platforms to address unmet needs and expectations. Although remote health technologies have addressed some of the medical needs, the emotional and mental well-being of these patients remain underexplored and underreported. We used a validated artificial intelligence framework to conduct a comprehensive real-time analysis of two data sets of 2,469,822 tweets and 21,800 discussions by patients with cancer during this pandemic. Lung and breast cancer are most prominently discussed, and the most concerns were expressed regarding delayed diagnosis, cancellations, missed treatments, and weakened immunity. All patients expressed significant negative sentiment, with fear being the predominant emotion. Even as some lockdown measures ease, it is crucial that patients with cancer are engaged using social media platforms for real-time identification of issues and the provision of informational and emotional support.

Emotions of COVID-19: Content Analysis of Self-Reported Information Using Artificial Intelligence.

BACKGROUND: The COVID-19 pandemic has disrupted human societies around the world. This public health emergency was followed by a significant loss of human life; the ensuing social restrictions led to loss of employment, lack of interactions, and burgeoning psychological distress. As physical distancing regulations were introduced to manage outbreaks, individuals, groups, and communities engaged extensively on social media to express their thoughts and emotions. This internet-mediated communication of self-reported information encapsulates the emotional health and mental well-being of all individuals impacted by the pandemic. OBJECTIVE: This research aims to investigate the human emotions related to the COVID-19 pandemic expressed on social media over time, using an artificial intelligence (AI) framework. METHODS: Our study explores emotion classifications, intensities, transitions, and profiles, as well as alignment to key themes and topics, across the four stages of the pandemic: declaration of a global health crisis (ie, prepandemic), the first lockdown, easing of restrictions, and the second lockdown. This study employs an AI framework comprised of natural language processing, word embeddings, Markov models, and the growing self-organizing map algorithm, which are collectively used to investigate social media conversations. The investigation was carried out using 73,000 public Twitter conversations posted by users in Australia from January to September 2020. RESULTS: The outcomes of this study enabled us to analyze and visualize different emotions and related concerns that were expressed and reflected on social media during the COVID-19 pandemic, which could be used to gain insights into citizens' mental health. First, the topic analysis showed the diverse as well as common concerns people had expressed during the four stages of the pandemic. It was noted that personal-level concerns expressed on social media had escalated to broader concerns over time. Second, the emotion intensity and emotion state transitions showed that fear and sadness emotions were more prominently expressed at first; however, emotions transitioned into anger and disgust over time. Negative emotions, except for sadness, were significantly higher (P<.05) in the second lockdown, showing increased frustration. Temporal emotion analysis was conducted by modeling the emotion state changes across the four stages of the pandemic, which demonstrated how different emotions emerged and shifted over time. Third, the concerns expressed by social media users were categorized into profiles, where differences could be seen between the first and second lockdown profiles. CONCLUSIONS: This study showed that the diverse emotions and concerns that were expressed and recorded on social media during the COVID-19 pandemic reflected the mental health of the general public. While this study established the use of social media to discover informed insights during a time when physical communication was impossible, the outcomes could also contribute toward postpandemic recovery and understanding psychological impact via emotion changes, and they could potentially inform health care decision making. This study exploited AI and social media to enhance our understanding of human behaviors in global emergencies, which could lead to improved planning and policy making for future crises.

Deep Learning to Predict Energy Expenditure and Activity Intensity in Free Living Conditions using Wrist-specific Accelerometry.

Wrist-worn accelerometers are more comfortable and yield greater compliance than hip-worn devices, making them attractive for free-living activity assessments. However, intricate wrist movements may require more complex predictive models than those applied to hip-worn devices. This study developed a novel deep learning method that predicts energy expenditure and physical activity intensity of adults using wrist-specific accelerometry. Triaxial accelerometers were worn by 119 participants on their wrist and hip for two weeks during waking hours. A deep learning model was developed from week 1 data of 60 participants and tested using week 2 data for: (i) the remaining 59 participants (Group UT), and (ii) participants used for training (Group TR). Estimates of physical activity were compared to a reference hip-specific method. Moderate-to-vigorous physical activity predicted by the wrist-model was not different to the reference method for participants in Group UT (5.9±3.1vs. 6.3±3.3 hour/week) and Group TR (6.9±3.7 vs. 7.2±4.2 hour/week). At 60-s epoch level, energy expenditure predicted by the wrist-model on Group UT was strongly correlated with the reference method (r=0.86, 95%CI: 0.84-0.87) and closely predicted activity intensity (83.7%, 95%CI: 80.9-86.5%). The deep learning method has application for wrist-worn accelerometry in free-living adults.

Finding the Intersection of Neuroplasticity, Stroke Recovery, and Learning: Scope and Contributions to Stroke Rehabilitation.

Aim: Neural plastic changes are experience and learning dependent, yet exploiting this knowledge to enhance clinical outcomes after stroke is in its infancy. Our aim was to search the available evidence for the core concepts of neuroplasticity, stroke recovery, and learning; identify links between these concepts; and identify and review the themes that best characterise the intersection of these three concepts. Methods: We developed a novel approach to identify the common research topics among the three areas: neuroplasticity, stroke recovery, and learning. A concept map was created a priori, and separate searches were conducted for each concept. The methodology involved three main phases: data collection and filtering, development of a clinical vocabulary, and the development of an automatic clinical text processing engine to aid the process and identify the unique and common topics. The common themes from the intersection of the three concepts were identified. These were then reviewed, with particular reference to the top 30 articles identified as intersecting these concepts. Results: The search of the three concepts separately yielded 405,636 publications. Publications were filtered to include only human studies, generating 263,751 publications related to the concepts of neuroplasticity (n = 6,498), stroke recovery (n = 79,060), and learning (n = 178,193). A cluster concept map (network graph) was generated from the results; indicating the concept nodes, strength of link between nodes, and the intersection between all three concepts. We identified 23 common themes (topics) and the top 30 articles that best represent the intersecting themes. A time-linked pattern emerged. Discussion and Conclusions: Our novel approach developed for this review allowed the identification of the common themes/topics that intersect the concepts of neuroplasticity, stroke recovery, and learning. These may be synthesised to advance a neuroscience-informed approach to stroke rehabilitation. We also identified gaps in available literature using this approach. These may help guide future targeted research.

The Patient-Reported Information Multidimensional Exploration (PRIME) Framework for Investigating Emotions and Other Factors of Prostate Cancer Patients with Low Intermediate Risk Based on Online Cancer Support Group Discussions.

BACKGROUND: This study aimed to use the Patient Reported Information Multidimensional Exploration (PRIME) framework, a novel ensemble of machine-learning and deep-learning algorithms, to extract, analyze, and correlate self-reported information from Online Cancer Support Groups (OCSG) by patients (and partners of patients) with low intermediate-risk prostate cancer (PCa) undergoing radical prostatectomy (RP), external beam radiotherapy (EBRT), and active surveillance (AS), and to investigate its efficacy in quality-of-life (QoL) and emotion measures. METHODS: From patient-reported information on 10 OCSG, the PRIME framework automatically filtered and extracted conversations on low intermediate-risk PCa with active user participation. Side effects as well as emotional and QoL outcomes for 6084 patients were analyzed. RESULTS: Side-effect profiles differed between the methods analyzed, with men after RP having more urinary and sexual side effects and men after EBRT having more bowel symptoms. Key findings from the analysis of emotional expressions showed that PCa patients younger than 40 years expressed significantly high positive and negative emotions compared with other age groups, that partners of patients expressed more negative emotions than the patients, and that selected cohorts (< 40 years, > 70 years, partners of patients) have frequently used the same terms to express their emotions, which is indicative of QoL issues specific to those cohorts. CONCLUSION: Despite recent advances in patient-centerd care, patient emotions are largely overlooked, especially in younger men with a diagnosis of PCa and their partners. The authors present a novel approach, the PRIME framework, to extract, analyze, and correlate key patient factors. This framework improves understanding of QoL and identifies low intermediate-risk PCa patients who require additional support.

Extraction of high quality k-words for alignment-free sequence comparison.

The weighted Euclidean distance (D(2)) is one of the earliest dissimilarity measures used for alignment free comparison of biological sequences. This distance measure and its variants have been used in numerous applications due to its fast computation, and many variants of it have been subsequently introduced. The D(2) distance measure is based on the count of k-words in the two sequences that are compared. Traditionally, all k-words are compared when computing the distance. In this paper we show that similar accuracy in sequence comparison can be achieved by using a selected subset of k-words. We introduce a term variance based quality measure for identifying the important k-words. We demonstrate the application of the proposed technique in phylogeny reconstruction and show that up to 99% of the k-words can be filtered out for certain datasets, resulting in faster sequence comparison. The paper also presents an exploratory analysis based evaluation of optimal k-word values and discusses the impact of using subsets of k-words in such optimal instances.

From concept to practice: a scoping review of the application of AI to aphasia diagnosis and management.

PURPOSE: Aphasia is an acquired communication disability resulting from impairments in language processing following brain injury, most commonly stroke. People with aphasia experience difficulties in all modalities of language that impact their quality of life. Therefore, researchers have investigated the use of Artificial Intelligence (AI) to deliver innovative solutions in Aphasia management and rehabilitation. MATERIALS AND METHODS: We conducted a scoping review of the use of AI in aphasia research and rehabilitation to explore the evolution of AI applications to aphasia, the progression of technologies and applications. Furthermore, we aimed to identify gaps in the use of AI in Aphasia to highlight the potential areas where AI might add value. We analysed 77 studies to determine the research objectives, the history of AI techniques in Aphasia and their progression over time. RESULTS: Most of the studies focus on automated assessment using AI, with recent studies focusing on AI for therapy and personalised assistive systems. Starting from prototypes and simulations, the use of AI has progressed to include supervised machine learning, unsupervised machine learning, natural language processing, fuzzy rules, and genetic programming. CONCLUSION: Considerable scope remains to align AI technology with aphasia rehabilitation to empower patient-centred, customised rehabilitation and enhanced self-management.

Aphasia is an acquired communication disorder that impacts everyday functioning due to impairments in speech, auditory comprehension, reading, and writing.Given this communication burden, researchers have focused on utilising artificial intelligence (AI) methods for assessment, therapy and self-management.From a conceptualisation era in the early 1940s, the application of AI has evolved with significant developments in AI applications at different points in time.Despite these developments, there are ample opportunities to exploit the use of AI to deliver more advanced applications in self-management and personalising care.

A Two-Layer Self-Organizing Map with Vector Symbolic Architecture for Spatiotemporal Sequence Learning and Prediction.

We propose a new nature- and neuro-science-inspired algorithm for spatiotemporal learning and prediction based on sequential recall and vector symbolic architecture. A key novelty is the learning of spatial and temporal patterns as decoupled concepts where the temporal pattern sequences are constructed using the learned spatial patterns as an alphabet of elements. The decoupling, motivated by cognitive neuroscience research, provides the flexibility for fast and adaptive learning with dynamic changes to data and concept drift and as such is better suited for real-time learning and prediction. The algorithm further addresses several key computational requirements for predicting the next occurrences based on real-life spatiotemporal data, which have been found to be challenging with current state-of-the-art algorithms. Firstly, spatial and temporal patterns are detected using unsupervised learning from unlabeled data streams in changing environments; secondly, vector symbolic architecture (VSA) is used to manage variable-length sequences; and thirdly, hyper dimensional (HD) computing-based associative memory is used to facilitate the continuous prediction of the next occurrences in sequential patterns. The algorithm has been empirically evaluated using two benchmark and three time-series datasets to demonstrate its advantages compared to the state-of-the-art in spatiotemporal unsupervised sequence learning where the proposed ST-SOM algorithm is able to achieve 45% error reduction compared to HTM algorithm.

Profiling Somatosensory Impairment after Stroke: Characterizing Common "Fingerprints" of Impairment Using Unsupervised Machine Learning-Based Cluster Analysis of Quantitative Measures of the Upper Limb.

Altered somatosensory function is common among stroke survivors, yet is often poorly characterized. Methods of profiling somatosensation that illustrate the variability in impairment within and across different modalities remain limited. We aimed to characterize post-stroke somatosensation profiles ("fingerprints") of the upper limb using an unsupervised machine learning cluster analysis to capture hidden relationships between measures of touch, proprioception, and haptic object recognition. Raw data were pooled from six studies where multiple quantitative measures of upper limb somatosensation were collected from stroke survivors (n = 207) using the Tactile Discrimination Test (TDT), Wrist Position Sense Test (WPST) and functional Tactile Object Recognition Test (fTORT) on the contralesional and ipsilesional upper limbs. The Growing Self Organizing Map (GSOM) unsupervised machine learning algorithm was used to generate a topology-preserving two-dimensional mapping of the pooled data and then separate it into clusters. Signature profiles of somatosensory impairment across two modalities (TDT and WPST; n = 203) and three modalities (TDT, WPST, and fTORT; n = 141) were characterized for both hands. Distinct impairment subgroups were identified. The influence of background and clinical variables was also modelled. The study provided evidence of the utility of unsupervised cluster analysis that can profile stroke survivor signatures of somatosensory impairment, which may inform improved diagnosis and characterization of impairment patterns.

An artificial intelligence life cycle: From conception to production.

This paper presents the "CDAC AI life cycle," a comprehensive life cycle for the design, development, and deployment of artificial intelligence (AI) systems and solutions. It addresses the void of a practical and inclusive approach that spans beyond the technical constructs to also focus on the challenges of risk analysis of AI adoption, transferability of prebuilt models, increasing importance of ethics and governance, and the composition, skills, and knowledge of an AI team required for successful completion. The life cycle is presented as the progression of an AI solution through its distinct phases-design, develop, and deploy-and 19 constituent stages from conception to production as applicable to any AI initiative. This life cycle addresses several critical gaps in the literature where related work on approaches and methodologies are adapted and not designed specifically for AI. A technical and organizational taxonomy that synthesizes the functional value of AI is a further contribution of this article.

Automated Design of Multipass Heuristics for Resource-Constrained Job Scheduling With Self-Competitive Genetic Programming.

Resource constraint job scheduling is an important combinatorial optimization problem with many practical applications. This problem aims at determining a schedule for executing jobs on machines satisfying several constraints (e.g., precedence and resource constraints) given a shared central resource while minimizing the tardiness of the jobs. Due to the complexity of the problem, several exact, heuristic, and hybrid methods have been attempted. Despite their success, scalability is still a major issue of the existing methods. In this study, we develop a new genetic programming algorithm for resource constraint job scheduling to overcome or alleviate the scalability issue. The goal of the proposed algorithm is to evolve effective and efficient multipass heuristics by a surrogate-assisted learning mechanism and self-competitive genetic operations. The experiments show that the evolved multipass heuristics are very effective when tested with a large dataset. Moreover, the algorithm scales very well as excellent solutions are found for even the largest problem instances, outperforming existing metaheuristic and hybrid methods.

Hyperseed: Unsupervised Learning With Vector Symbolic Architectures.

Motivated by recent innovations in biologically inspired neuromorphic hardware, this article presents a novel unsupervised machine learning algorithm named Hyperseed that draws on the principles of vector symbolic architectures (VSAs) for fast learning of a topology preserving feature map of unlabeled data. It relies on two major operations of VSA, binding and bundling. The algorithmic part of Hyperseed is expressed within the Fourier holographic reduced representations (FHRR) model, which is specifically suited for implementation on spiking neuromorphic hardware. The two primary contributions of the Hyperseed algorithm are few-shot learning and a learning rule based on single vector operation. These properties are empirically evaluated on synthetic datasets and on illustrative benchmark use cases, IRIS classification, and a language identification task using the n -gram statistics. The results of these experiments confirm the capabilities of Hyperseed and its applications in neuromorphic hardware.

Providing Care Beyond Therapy Sessions With a Natural Language Processing-Based Recommender System That Identifies Cancer Patients Who Experience Psychosocial Challenges and Provides Self-care Support: Pilot Study.

BACKGROUND: The negative psychosocial impacts of cancer diagnoses and treatments are well documented. Virtual care has become an essential mode of care delivery during the COVID-19 pandemic, and online support groups (OSGs) have been shown to improve accessibility to psychosocial and supportive care. de Souza Institute offers CancerChatCanada, a therapist-led OSG service where sessions are monitored by an artificial intelligence-based co-facilitator (AICF). The AICF is equipped with a recommender system that uses natural language processing to tailor online resources to patients according to their psychosocial needs. OBJECTIVE: We aimed to outline the development protocol and evaluate the AICF on its precision and recall in recommending resources to cancer OSG members. METHODS: Human input informed the design and evaluation of the AICF on its ability to (1) appropriately identify keywords indicating a psychosocial concern and (2) recommend the most appropriate online resource to the OSG member expressing each concern. Three rounds of human evaluation and algorithm improvement were performed iteratively. RESULTS: We evaluated 7190 outputs and achieved a precision of 0.797, a recall of 0.981, and an F1 score of 0.880 by the third round of evaluation. Resources were recommended to 48 patients, and 25 (52%) accessed at least one resource. Of those who accessed the resources, 19 (75%) found them useful. CONCLUSIONS: The preliminary findings suggest that the AICF can help provide tailored support for cancer OSG members with high precision, recall, and satisfaction. The AICF has undergone rigorous human evaluation, and the results provide much-needed evidence, while outlining potential strengths and weaknesses for future applications in supportive care.

People-Centric Evolutionary System for Dynamic Production Scheduling.

Evolving production scheduling heuristics is a challenging task because of the dynamic and complex production environments and the interdependency of multiple scheduling decisions. Different genetic programming (GP) methods have been developed for this task and achieved very encouraging results. However, these methods usually have trouble in discovering powerful and compact heuristics, especially for difficult problems. Moreover, there is no systematic approach for the decision makers to intervene and embed their knowledge and preferences in the evolutionary process. This article develops a novel people-centric evolutionary system for dynamic production scheduling. The two key components of the system are a new mapping technique to incrementally monitor the evolutionary process and a new adaptive surrogate model to improve the efficiency of GP. The experimental results with dynamic flexible job shop scheduling show that the proposed system outperforms the existing algorithms for evolving scheduling heuristics in terms of scheduling performance and heuristic sizes. The new system also allows the decision makers to interact on the fly and guide the evolution toward the desired solutions.