Search

Detecting falls among the elderly and alerting their community responders can save countless lives. We design and develop a low-cost mobile robot that periodically searches the house for the person being monitored and sends an email to a set of designated responders if a fall is detected. In this project, we make three novel design decisions and contributions. First, our custom-designed low-cost robot has advanced features like omnidirectional wheels, the ability to run deep learning models, and autonomous wireless charging. Second, we improve the accuracy of fall detection for the YOLOv8-Pose-nano object detection network by 6% and YOLOv8-Pose-large by 12%. We do so by transforming the images captured from the robot viewpoint (camera height 0.15m from the ground) to a typical human viewpoint (1.5m above the ground) using a principally computed Homography matrix. This improves network accuracy because the training dataset MS-COCO on which YOLOv8-Pose is trained is captured from a human-height viewpoint. Lastly, we improve the robot controller by learning a model that predicts the robot velocity from the input signal to the motor controller., Comment: Accepted to IEEE AIM-2024

Cross-view geo-localization has garnered notable attention in the realm of computer vision, spurred by the widespread availability of copious geotagged datasets and the advancements in machine learning techniques. This paper provides a thorough survey of cutting-edge methodologies, techniques, and associated challenges that are integral to this domain, with a focus on feature-based and deep learning strategies. Feature-based methods capitalize on unique features to establish correspondences across disparate viewpoints, whereas deep learning-based methodologies deploy convolutional neural networks to embed view-invariant attributes. This work also delineates the multifaceted challenges encountered in cross-view geo-localization, such as variations in viewpoints and illumination, the occurrence of occlusions, and it elucidates innovative solutions that have been formulated to tackle these issues. Furthermore, we delineate benchmark datasets and relevant evaluation metrics, and also perform a comparative analysis of state-of-the-art techniques. Finally, we conclude the paper with a discussion on prospective avenues for future research and the burgeoning applications of cross-view geo-localization in an intricately interconnected global landscape.

Deep learning algorithms have seen acute growth of interest in their applications throughout several fields of interest in the last decade, with medical hyperspectral imaging being a particularly promising domain. So far, to the best of our knowledge, there is no review paper that discusses the implementation of deep learning for medical hyperspectral imaging, which is what this review paper aims to accomplish by examining publications that currently utilize deep learning to perform effective analysis of medical hyperspectral imagery. This paper discusses deep learning concepts that are relevant and applicable to medical hyperspectral imaging analysis, several of which have been implemented since the boom in deep learning. This will comprise of reviewing the use of deep learning for classification, segmentation, and detection in order to investigate the analysis of medical hyperspectral imaging. Lastly, we discuss the current and future challenges pertaining to this discipline and the possible efforts to overcome such trials.

U-net is an image segmentation technique developed primarily for medical image analysis that can precisely segment images using a scarce amount of training data. These traits provide U-net with a very high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in all major image modalities from CT scans and MRI to X-rays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. As the potential of U-net is still increasing, in this review we look at the various developments that have been made in the U-net architecture and provide observations on recent trends. We examine the various innovations that have been made in deep learning and discuss how these tools facilitate U-net. Furthermore, we look at image modalities and application areas where U-net has been applied., Comment: 42 pages, in IEEE Access

At the time of writing this paper, the world has around eleven million cases of COVID-19, scientifically known as severe acute respiratory syndrome corona-virus 2 (SARS-COV-2). One of the popular critical steps various health organizations are advocating to prevent the spread of this contagious disease is self-assessment of symptoms. Multiple organizations have already pioneered mobile and web-based applications for self-assessment of COVID-19 to reduce this global pandemic's spread. We propose an intelligent voice-based assistant for COVID-19 self-assessment (IVACS). This interactive assistant has been built to diagnose the symptoms related to COVID-19 using the guidelines provided by the Centers for Disease Control and Prevention (CDC) and the World Health Organization (WHO). The empirical testing of the application has been performed with 22 human subjects, all volunteers, using the NASA Task Load Index (TLX), and subjects performance accuracy has been measured. The results indicate that the IVACS is beneficial to users. However, it still needs additional research and development to promote its widespread application.

As part of a perennial project, our team is actively engaged in developing new synthetic assistant (SA) technologies to assist in training combat medics and medical first responders. It is critical that medical first responders are well trained to deal with emergencies more effectively. This would require real-time monitoring and feedback for each trainee. Therefore, we introduced a voice-based SA to augment the training process of medical first responders and enhance their performance in the field. The potential benefits of SAs include a reduction in training costs and enhanced monitoring mechanisms. Despite the increased usage of voice-based personal assistants (PAs) in day-to-day life, the associated effects are commonly neglected for a study of human factors. Therefore, this paper focuses on performance analysis of the developed voice-based SA in emergency care provider training for a selected emergency treatment scenario. The research discussed in this paper follows design science in developing proposed technology; at length, we discussed architecture and development and presented working results of voice-based SA. The empirical testing was conducted on two groups as user studies using statistical analysis tools, one trained with conventional methods and the other with the help of SA. The statistical results demonstrated the amplification in training efficacy and performance of medical responders powered by SA. Furthermore, the paper also discusses the accuracy and time of task execution (t) and concludes with the guidelines for resolving the identified problems.

Computing and intelligence are substantial requirements for the accurate performance of autonomous ground vehicles (AGVs). In this context, the use of cloud services in addition to onboard computers enhances computing and intelligence capabilities of AGVs. In addition, the vast amount of data processed in a cloud system contributes to overall performance and capabilities of the onboard system. This research study entails a qualitative analysis to gather insights on the applicability of the leading cloud service providers in AGV operations. These services include Google Cloud, Microsoft Azure, Amazon AWS, and IBM Cloud. The study begins with a brief review of AGV technical requirements that are necessary to determine the rationale for identifying the most suitable cloud service. The qualitative analysis studies and addresses the applicability of the cloud service over the proposed generalized AGV's architecture integration, performance, and manageability. Our findings conclude that a generalized AGV architecture can be supported by state-of-the-art cloud service, but there should be a clear line of separation between the primary and secondary computing needs. Moreover, our results show significant lags while using cloud services and preventing their use in real-time AGV operation.

A significant amount of work is invested in human-machine teaming (HMT) across multiple fields. Accurately and effectively measuring system performance of an HMT is crucial for moving the design of these systems forward. Metrics are the enabling tools to devise a benchmark in any system and serve as an evaluation platform for assessing the performance, along with the verification and validation, of a system. Currently, there is no agreed-upon set of benchmark metrics for developing HMT systems. Therefore, identification and classification of common metrics are imperative to create a benchmark in the HMT field. The key focus of this review is to conduct a detailed survey aimed at identification of metrics employed in different segments of HMT and to determine the common metrics that can be used in the future to benchmark HMTs. We have organized this review as follows: identification of metrics used in HMTs until now, and classification based on functionality and measuring techniques. Additionally, we have also attempted to analyze all the identified metrics in detail while classifying them as theoretical, applied, real-time, non-real-time, measurable, and observable metrics. We conclude this review with a detailed analysis of the identified common metrics along with their usage to benchmark HMTs.

On-line social networks (OSNs) often contain many different types of relationships between users. When studying the structure of OSNs such as Facebook, two of the most commonly studied networks are friendship and interaction networks. The link prediction problem in friendship networks has been heavily studied. There has also been prior work on link prediction in interaction networks, independent of friendship networks. In this paper, we study the predictive power of combining friendship and interaction networks. We hypothesize that, by leveraging friendship networks, we can improve the accuracy of link prediction in interaction networks. We augment several interaction link prediction algorithms to incorporate friendships and predicted friendships. From experiments on Facebook data, we find that incorporating friendships into interaction link prediction algorithms results in higher accuracy, but incorporating predicted friendships does not when compared to incorporating current friendships., Comment: To appear in ICWSM 2018. This version corrects some minor errors in Table 1. MATLAB code available at https://github.com/IdeasLabUT/Friendship-Interaction-Prediction

We consider the problem of analyzing timestamped relational events between a set of entities, such as messages between users of an on-line social network. Such data are often analyzed using static or discrete-time network models, which discard a significant amount of information by aggregating events over time to form network snapshots. In this paper, we introduce a block point process model (BPPM) for continuous-time event-based dynamic networks. The BPPM is inspired by the well-known stochastic block model (SBM) for static networks. We show that networks generated by the BPPM follow an SBM in the limit of a growing number of nodes. We use this property to develop principled and efficient local search and variational inference procedures initialized by regularized spectral clustering. We fit BPPMs with exponential Hawkes processes to analyze several real network data sets, including a Facebook wall post network with over 3,500 nodes and 130,000 events., Comment: To appear at The Web Conference 2019

The task of predicting future relationships in a social network, known as link prediction, has been studied extensively in the literature. Many link prediction methods have been proposed, ranging from common neighbors to probabilistic models. Recent work by Yang et al. has highlighted several challenges in evaluating link prediction accuracy. In dynamic networks where edges are both added and removed over time, the link prediction problem is more complex and involves predicting both newly added and newly removed edges. This results in new challenges in the evaluation of dynamic link prediction methods, and the recommendations provided by Yang et al. are no longer applicable, because they do not address edge removal. In this paper, we investigate several metrics currently used for evaluating accuracies of dynamic link prediction methods and demonstrate why they can be misleading in many cases. We provide several recommendations on evaluating dynamic link prediction accuracy, including separation into two categories of evaluation. Finally we propose a unified metric to characterize link prediction accuracy effectively using a single number., Comment: To appear in Proceedings of SocialCom 2016

Trilateration-based localization (TBL) has become a corner stone of modern technology. This study formulates the concern on how wireless sensor networks can take advantage of the computational intelligent techniques using both single- and multi-objective particle swarm optimization (PSO) with an overall aim of concurrently minimizing the required time for localization, minimizing energy consumed during localization, and maximizing the number of nodes fully localized through the adjustment of wireless sensor transmission ranges while using TBL process. A parameter-study of the applied PSO variants is performed, leading to results that show algorithmic improvements of up to 32% in the evaluated objectives., Comment: 19 Pages, 13 Figures, 10 Tables, Journal