Deep Reinforcement Learning in Human Activity Recognition: A Survey and Outlook.

Human activity recognition (HAR) is a popular research field in computer vision that has already been widely studied. However, it is still an active research field since it plays an important role in many current and emerging real-world intelligent systems, like visual surveillance and human-computer interaction. Deep reinforcement learning (DRL) has recently been used to address the activity recognition problem with various purposes, such as finding attention in video data or obtaining the best network structure. DRL-based HAR has only been around for a short time, and it is a challenging, novel field of study. Therefore, to facilitate further research in this area, we have constructed a comprehensive survey on activity recognition methods that incorporate DRL. Throughout the article, we classify these methods according to their shared objectives and delve into how they are ingeniously framed within the DRL framework. As we navigate through the survey, we conclude by shedding light on the prominent challenges and lingering questions that await the attention of future researchers, paving the way for further advancements and breakthroughs in this exciting domain.

Self-supervised anomaly detection in computer vision and beyond: A survey and outlook.

Anomaly detection (AD) plays a crucial role in various domains, including cybersecurity, finance, and healthcare, by identifying patterns or events that deviate from normal behavior. In recent years, significant progress has been made in this field due to the remarkable growth of deep learning models. Notably, the advent of self-supervised learning has sparked the development of novel AD algorithms that outperform the existing state-of-the-art approaches by a considerable margin. This paper aims to provide a comprehensive review of the current methodologies in self-supervised anomaly detection. We present technical details of the standard methods and discuss their strengths and drawbacks. We also compare the performance of these models against each other and other state-of-the-art anomaly detection models. Finally, the paper concludes with a discussion of future directions for self-supervised anomaly detection, including the development of more effective and efficient algorithms and the integration of these techniques with other related fields, such as multi-modal learning.

Artificial Intelligence for Detection of Dementia Using Motion Data: A Scoping Review.

Background: Dementia is a neurodegenerative disease resulting in the loss of cognitive and psychological functions. Artificial intelligence (AI) may help in detection and screening of dementia; however, little is known in this area. Objectives: The objective of this study was to identify and evaluate AI interventions for detection of dementia using motion data. Method: The review followed the framework proposed by O'Malley's and Joanna Briggs Institute methodological guidance for scoping reviews. We adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist for reporting the results. An information specialist performed a comprehensive search from the date of inception until November 2020, in five bibliographic databases: MEDLINE, EMBASE, Web of Science Core Collection, CINAHL, and IEEE Xplore. We included studies aimed at the deployment and testing or implementation of AI interventions using motion data for the detection of dementia among a diverse population, encompassing varying age, sex, gender, economic backgrounds, and ethnicity, extending to their health care providers across multiple health care settings. Studies were excluded if they focused on Parkinson's or Huntington's disease. Two independent reviewers screened the abstracts, titles, and then read the full-texts. Disagreements were resolved by consensus, and if this was not possible, the opinion of a third reviewer was sought. The reference lists of included studies were also screened. Results: After removing duplicates, 2,632 articles were obtained. After title and abstract screening and full-text screening, 839 articles were considered for categorization. The authors categorized the papers into six categories, and data extraction and synthesis was performed on 20 included papers from the motion tracking data category. The included studies assessed cognitive performance (n = 5, 25%); screened dementia and cognitive decline (n = 8, 40%); investigated visual behaviours (n = 4, 20%); and analyzed motor behaviors (n = 3, 15%). Conclusions: We presented evidence of AI systems being employed in the detection of dementia, showcasing the promising potential of motion tracking within this domain. Although some progress has been made in this field recently, there remain notable research gaps that require further exploration and investigation. Future endeavors need to compare AI interventions using motion data with traditional screening methods or other tech-enabled dementia detection mechanisms. Besides, future works should aim at understanding how gender and sex, and ethnic and cultural sensitivity can contribute to refining AI interventions, ensuring they are accessible, equitable, and beneficial across all society.

Deep Multirepresentation Learning for Data Clustering.

Deep clustering incorporates embedding into clustering in order to find a lower-dimensional space suitable for clustering tasks. Conventional deep clustering methods aim to obtain a single global embedding subspace (aka latent space) for all the data clusters. In contrast, in this article, we propose a deep multirepresentation learning (DML) framework for data clustering whereby each difficult-to-cluster data group is associated with its own distinct optimized latent space and all the easy-to-cluster data groups are associated with a general common latent space. Autoencoders (AEs) are employed for generating cluster-specific and general latent spaces. To specialize each AE in its associated data cluster(s), we propose a novel and effective loss function which consists of weighted reconstruction and clustering losses of the data points, where higher weights are assigned to the samples more probable to belong to the corresponding cluster(s). Experimental results on benchmark datasets demonstrate that the proposed DML framework and loss function outperform state-of-the-art clustering approaches. In addition, the results show that the DML method significantly outperforms the SOTA on imbalanced datasets as a result of assigning an individual latent space to the difficult clusters.

Tools and Techniques for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2)/COVID-19 Detection.

The coronavirus disease 2019 (COVID-19) pandemic, caused by severe acute respiratory disease coronavirus 2 (SARS-CoV-2), has led to millions of confirmed cases and deaths worldwide. Efficient diagnostic tools are in high demand, as rapid and large-scale testing plays a pivotal role in patient management and decelerating disease spread. This paper reviews current technologies used to detect SARS-CoV-2 in clinical laboratories as well as advances made for molecular, antigen-based, and immunological point-of-care testing, including recent developments in sensor and biosensor devices. The importance of the timing and type of specimen collection is discussed, along with factors such as disease prevalence, setting, and methods. Details of the mechanisms of action of the various methodologies are presented, along with their application span and known performance characteristics. Diagnostic imaging techniques and biomarkers are also covered, with an emphasis on their use for assessing COVID-19 or monitoring disease severity or complications. While the SARS-CoV-2 literature is rapidly evolving, this review highlights topics of interest that have occurred during the pandemic and the lessons learned throughout. Exploring a broad armamentarium of techniques for detecting SARS-CoV-2 will ensure continued diagnostic support for clinicians, public health, and infection prevention and control for this pandemic and provide advice for future pandemic preparedness.

Multiview Feature Selection for Single-View Classification.

In many real-world scenarios, data from multiple modalities (sources) are collected during a development phase. Such data are referred to as multiview data. While additional information from multiple views often improves the performance, collecting data from such additional views during the testing phase may not be desired due to the high costs associated with measuring such views or, unavailability of such additional views. Therefore, in many applications, despite having a multiview training data set, it is desired to do performance testing using data from only one view. In this paper, we present a multiview feature selection method that leverages the knowledge of all views and use it to guide the feature selection process in an individual view. We realize this via a multiview feature weighting scheme such that the local margins of samples in each view are maximized and similarities of samples to some reference points in different views are preserved. Also, the proposed formulation can be used for cross-view matching when the view-specific feature weights are pre-computed on an auxiliary data set. Promising results have been achieved on nine real-world data sets as well as three biometric recognition applications. On average, the proposed feature selection method has improved the classification error rate by 31 percent of the error rate of the state-of-the-art.

Quantification of Resting-State Ballistocardiogram Difference Between Clinical and Non-Clinical Populations for Ambient Monitoring of Heart Failure.

A ballistocardiogram (BCG) is a versatile bio-signal that enables ambient remote monitoring of heart failure (HF) patients in a home setting, achieved through embedded sensors in the surrounding environment. Numerous methods of analysis are available for extracting physiological information using the BCG; however, most have been developed based on non-clinical subjects. While the difference between clinical and non-clinical populations are expected, quantification of the difference may serve as a useful tool. In this work, the differences in resting-state BCGs of the two cohorts in a sitting posture were quantified. An instrumented chair was used to collect the BCG from 29 healthy adults and 26 NYHA HF class I and II patients while seated without any stress test for five minutes. Five 20-second epochs per subject were used to calculate the waveform fluctuation metric at rest (WFMR). The WFMR was obtained in two steps. The ensemble average of the segmented BCG heartbeats within an epoch were calculated first. Mean square errors (MSE) between different ensemble average pairs were then retrieved. The MSEs were averaged to produce the WFMR. The comparison showed that the clinical cohort had higher fluctuation than the non-clinical population and had at least 82.2% separation, suggesting that greater errors may result when existing algorithms were used. The WFMR acts as a bridge that may enable important features, including the addition of error margins in parameter estimation and ways to devise a calibration strategy when resting-state BCG is unstable.

A Machine Learning Framework for Automatic and Continuous MMN Detection With Preliminary Results for Coma Outcome Prediction.

Mismatch negativity (MMN) is a component of the event-related potential (ERP) that is elicited through an odd-ball paradigm. The existence of the MMN in a coma patient has a good correlation with coma emergence; however, this component can be difficult to detect. Previously, MMN detection was based on visual inspection of the averaged ERPs by a skilled clinician, a process that is expensive and not always feasible in practice. In this paper, we propose a practical machine learning (ML) based approach for detection of MMN component, thus, improving the accuracy of prediction of emergence from coma. Furthermore, the method can operate on an automatic and continuous basis thus alleviating the need for clinician involvement. The proposed method is capable of the MMN detection over intervals as short as two minutes. This finer time resolution enables identification of waxing and waning cycles of a conscious state. An auditory odd-ball paradigm was applied to 22 healthy subjects and 2 coma patients. A coma patient is tested by measuring the similarity of the patient's ERP responses with the aggregate healthy responses. Because the training process for measuring similarity requires only healthy subjects, the complexity and practicality of training procedure of the proposed method are greatly improved relative to training on coma patients directly. Since there are only two coma patients involved with this study, the results are reported on a very preliminary basis. Preliminary results indicate we can detect the MMN component with an accuracy of 92.7% on healthy subjects. The method successfully predicted emergence in both coma patients when conventional methods failed. The proposed method for collecting training data using exclusively healthy subjects is a novel approach that may prove useful in future, unrelated studies where ML methods are used.

Development of a Smart Home-Based Package for Unobtrusive Physiological Monitoring.

Home-based programs have been shown to be effective in improving health conditions, patient self-management, quality of life, and health outcomes. However, there is mixedevidence on the effectiveness of these programs due to limitations in the intervention tools that are used, primarily the burden that is placed on the user, especially among seniors. In this paper we developed a novel home-based package that measures critically important physiological information such that neither active compliance or interaction from the user is required. To this end, we embedded passive sensors (including load cells, electrodes, pulse sensor and color sensors) into common household items such as tiling, furniture and wall. The smart package measures subject's electrocardiogram (ECG), photoplethysmogram (PPG), ballistocardiogram (BCG), electromyogram (EMG) and imaging photoplethysmogram (IPPG). In contrast to the previous studies, the proposed package measures all the physiological information unobtrusively, simultaneously and in a synchronized manner such that all the data samples corresponding to different intervals of a specific cardiovascular cycle can be identified. Such information can be analyzed by a clinician or be used for a higher level information extraction such as beat-to-beat blood pressure estimation. In addition, the proposed package is the first and only homebased technology that can simultaneously and unobtrusively capture both mechanical and electrical characteristics of user's heart activities. This results in a more accurate home-based vital parameters monitoring.

Unobtrusive Detection of Simulated Orthostatic Hypotension and Supine Hypertension Using Ballistocardiogram and Electrocardiogram of Healthy Adults.

Effective management of neurogenic orthostatic hypotension and supine hypertension (SH-OH) due autonomic failure requires a frequent and timely adjustment of medication throughout the day to maintain the blood pressure (BP) within the normal range, i.e., an accurate depiction of BP is a key prerequisite of effective management. One of the emerging technologies that provide one's circadian and long-term physiological status with increased usability is unobtrusive zero-effort monitoring. In this paper, a zero-effort device, a floor tile, was used to develop an unobtrusive BP monitoring technique. Namely, RJ-interval, the time between the J-peak of a ballistocardiogram and the R-peak of an electrocardiogram, was used to develop a classifier that can detect changes in systolic BP (SBP) induced by the Valsalva maneuver on healthy adults (i.e., a simulated SH-OH). A t-test was used to show statistical differences between the mean RJ-intervals of decreased SBP, baseline, and increased SBP. Following the t-test, a classifier that detected a change in SBP was developed based on a naïve Bayes classifier (NBC). The t-test showed a clear statistical difference between the mean RJ-intervals of the increased SBP, baseline, and decreased SBP. The NBC-based classifier was able to detect increased SBP with 89.3% true positive rate (TPR), 100% true negative rate (TNR), and 94% accuracy and detect decreased SBP with 92.3% TPR, 100% TNR, and 95% accuracy. The analysis showed strong potential in using the developed classifier to assist monitoring of people with SH-OH; the algorithm may be used clinically to detect a long-term trend of symptoms of SH-OH.

Logistic Localized Modeling of the Sample Space for Feature Selection and Classification.

Conventional feature selection algorithms assign a single common feature set to all regions of the sample space. In contrast, this paper proposes a novel algorithm for localized feature selection for which each region of the sample space is characterized by its individual distinct feature subset that may vary in size and membership. This approach can therefore select an optimal feature subset that adapts to local variations of the sample space, and hence offer the potential for improved performance. Feature subsets are computed by choosing an optimal coordinate space so that, within a localized region, within-class distances and between-class distances are, respectively, minimized and maximized. Distances are measured using a logistic function metric within the corresponding region. This enables the optimization process to focus on a localized region within the sample space. A local classification approach is utilized for measuring the similarity of a new input data point to each class. The proposed logistic localized feature selection (lLFS) algorithm is invariant to the underlying probability distribution of the data; hence, it is appropriate when the data are distributed on a nonlinear or disjoint manifold. lLFS is efficiently formulated as a joint convex/increasing quasi-convex optimization problem with a unique global optimum point. The method is most applicable when the number of available training samples is small. The performance of the proposed localized method is successfully demonstrated on a large variety of data sets. We demonstrate that the number of features selected by the lLFS method saturates at the number of available discriminative features. In addition, we have shown that the Vapnik-Chervonenkis dimension of the localized classifier is finite. Both these factors suggest that the lLFS method is insensitive to the overfitting issue, relative to other methods.

Feature Selection for Nonstationary Data: Application to Human Recognition Using Medical Biometrics.

Electrocardiogram (ECG) and transient evoked otoacoustic emission (TEOAE) are among the physiological signals that have attracted significant interest in biometric community due to their inherent robustness to replay and falsification attacks. However, they are time-dependent signals and this makes them hard to deal with in across-session human recognition scenario where only one session is available for enrollment. This paper presents a novel feature selection method to address this issue. It is based on an auxiliary dataset with multiple sessions where it selects a subset of features that are more persistent across different sessions. It uses local information in terms of sample margins while enforcing an across-session measure. This makes it a perfect fit for aforementioned biometric recognition problem. Comprehensive experiments on ECG and TEOAE variability due to time lapse and body posture are done. Performance of the proposed method is compared against seven state-of-the-art feature selection algorithms as well as another six approaches in the area of ECG and TEOAE biometric recognition. Experimental results demonstrate that the proposed method performs noticeably better than other algorithms.

Local Feature Selection for Data Classification.

Typical feature selection methods choose an optimal global feature subset that is applied over all regions of the sample space. In contrast, in this paper we propose a novel localized feature selection (LFS) approach whereby each region of the sample space is associated with its own distinct optimized feature set, which may vary both in membership and size across the sample space. This allows the feature set to optimally adapt to local variations in the sample space. An associated method for measuring the similarities of a query datum to each of the respective classes is also proposed. The proposed method makes no assumptions about the underlying structure of the samples; hence the method is insensitive to the distribution of the data over the sample space. The method is efficiently formulated as a linear programming optimization problem. Furthermore, we demonstrate the method is robust against the over-fitting problem. Experimental results on eleven synthetic and real-world data sets demonstrate the viability of the formulation and the effectiveness of the proposed algorithm. In addition we show several examples where localized feature selection produces better results than a global feature selection method.

Automatic and continuous assessment of ERPs for mismatch negativity detection.

Accurate and fast detection of event related potential (ERP) components is an unresolved issue in neuroscience and critical health care. Mismatch negativity (MMN) is a component of the ERP to an odd stimulus in a sequence of identical stimuli which has good correlation with coma awakening. All of the previous studies for MMN detection are based on visual inspection of the averaged ERPs (over a long recording time) by a skilled neurophysiologist. However, in practical situations, such an expert may not be available or familiar with all aspects of evoked potential methods. Further, we may miss important clinically essential events due to the implicit averaging process used to acquire the ERPs. In this paper we propose a practical machine learning approach for automatic and continuous assessment of the ERPs for detecting the presence of the MMN component. The proposed method is realized in a classification framework. Performance of the proposed method is demonstrated on 22 healthy subjects through a leave-one subject-out strategy where the MMN components are identified with about 93% accuracy.