We report a novel non-contact method for dehydration monitoring. We utilize a transmit software defined radio (SDR) that impinges a wideband radio frequency (RF) signal (of frequency 5.23 GHz) onto either the chest or the hand of a subject who sits nearby. Further, another SDR in the closed vicinity collects the RF signals reflected off the chest (or passed through the hand) of the subject. Note that the two SDRs exchange orthogonal frequency division multiplexing (OFDM) signal, whose individual subcarriers get modulated once it reflects off (passes through) the chest (the hand) of the subject. This way, the signal collected by the receive SDR consists of channel frequency response (CFR) that captures the variation in the blood osmolality due to dehydration. The received raw CFR data is then passed through a handful of machine learning (ML) classifiers which once trained, output the classification result (i.e., whether a subject is hydrated or dehydrated). For the purpose of training our ML classifiers, we have constructed our custom HCDDM-RF-5 dataset by collecting data from 5 Muslim subjects (before and after sunset) who were fasting during the month of Ramadan. Specifically, we have implemented and tested the following ML classifiers (and their variants): K-nearest neighbour (KNN), support vector machine (SVM), decision tree (DT), ensemble classifier, and neural network classifier. Among all the classifiers, the neural network classifier acheived the best classification accuracy, i.e., an accuracy of 93.8% for the proposed CBDM method, and an accuracy of 96.15% for the proposed HBDM method. Compared to prior work where the reported accuracy is 97.83%, our proposed non-contact method is slightly inferior (as we report a maximum accuracy of 96.15%); nevertheless, the advantages of our non-contact dehydration method speak for themselves.
相關內容
機器學習系統(tong)(tong)設計(ji)系統(tong)(tong)評估標準(zhun)
The Internet of Things (IoT) devices are rapidly increasing in popularity, with more individuals using Internet-connected devices that continuously monitor their activities. This work explores privacy concerns and expectations of end-users related to Trigger-Action platforms (TAPs) in the context of the Internet of Things (IoT). TAPs allow users to customize their smart environments by creating rules that trigger actions based on specific events or conditions. As personal data flows between different entities, there is a potential for privacy concerns. In this study, we aimed to identify the privacy factors that impact users' concerns and preferences for using IoT TAPs. To address this research objective, we conducted three focus groups with 15 participants and we extracted nine themes related to privacy factors using thematic analysis. Our participants particularly prefer to have control and transparency over the automation and are concerned about unexpected data inferences, risks and unforeseen consequences for themselves and for bystanders that are caused by the automation. The identified privacy factors can help researchers derive predefined and selectable profiles of privacy permission settings for IoT TAPs that represent the privacy preferences of different types of users as a basis for designing usable privacy controls for IoT TAPs.
Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data. However, GNN-based diagnosis of neurological disorders, such as Alzheimer's disease (AD), remains a relatively unexplored area of research. Previous studies have relied on functional connectivity methods to infer brain graph structures and used simple GNN architectures for the diagnosis of AD. In this work, we propose a novel adaptive gated graph convolutional network (AGGCN) that can provide explainable predictions. AGGCN adaptively learns graph structures by combining convolution-based node feature enhancement with a well-known correlation-based measure of functional connectivity. Furthermore, the gated graph convolution can dynamically weigh the contribution of various spatial scales. The proposed model achieves high accuracy in both eyes-closed and eyes-open conditions, indicating the stability of learned representations. Finally, we demonstrate that the proposed AGGCN model generates consistent explanations of its predictions that might be relevant for further study of AD-related alterations of brain networks.
In this paper, the digital self-interference (SI) cancellation in a single radio frequency (RF) chain massive multi-input multi-output (MIMO) full-duplex (FD) orthogonal frequency division multiplexing (OFDM) system with phase noise is studied. To compensate the phase noise, which introduces SI channel estimation error and thus degrades the SI cancellation performance, a weighted linear SI channel estimator is derived to minimize the residual SI power in each OFDM symbol. The digital SI cancellation ability of the proposed method, which is defined as the ratio of the SI power before and after the SI cancellation, is analyzed. Simulation results show that the proposed optimal linear SI channel estimator significantly outperforms the conventional least square (LS) estimator in terms of the SI cancellation ability for the cases with strong SI and low oscillator quality.
Air interface is a fundamental component within any wireless communication system. In Release 18, the 3rd Generation Partnership Project (3GPP) delves into the possibilities of leveraging artificial intelligence (AI)/machine learning (ML) to improve the performance of the fifth-generation (5G) New Radio (NR) air interface. This endeavor marks a pioneering stride within 3GPP's journey in shaping wireless communication standards. This article offers a comprehensive overview of the pivotal themes explored by 3GPP in this domain. Encompassing a general framework for AI/ML and specific use cases such as channel state information feedback, beam management, and positioning, it provides a holistic perspective. Moreover, we highlight the potential trajectory of AI/ML for the NR air interface in 3GPP Release 19, a pathway that paves the journey towards the sixth generation (6G) wireless communication systems that will feature integrated AI and communication as a key usage scenario.
Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment. In this study, we propose the integration of two commonly used approaches in privacy preservation: source separation and adversarial representation learning. The proposed system learns the latent representation of audio recordings such that it prevents differentiating between speech and non-speech recordings. Initially, the source separation network filters out some of the privacy-sensitive data, and during the adversarial learning process, the system will learn privacy-preserving representation on the filtered signal. We demonstrate the effectiveness of our proposed method by comparing our method against systems without source separation, without adversarial learning, and without both. Overall, our results suggest that the proposed system can significantly improve speech privacy preservation compared to that of using source separation or adversarial learning solely while maintaining good performance in the acoustic monitoring task.
Metaverse enables users to communicate, collaborate and socialize with each other through their digital avatars. Due to the spatio-temporal characteristics, co-located users are served well by performing their software components in a collaborative manner such that a Metaverse service provider (MSP) eliminates redundant data transmission and processing, ultimately reducing the total energy consumption. The energyefficient service provision is crucial for enabling the green and sustainable Metaverse. In this article, we take an augmented reality (AR) application as an example to achieve this goal. Moreover, we study an economic issue on how the users reserve offloading services from the MSP and how the MSP determines an optimal charging price since each user is rational to decide whether to accept the offloading service by taking into account the monetary cost. A single-leader multi-follower Stackelberg game is formulated between the MSP and users while each user optimizes an offloading probability to minimize the weighted sum of time, energy consumption and monetary cost. Numerical results show that our scheme achieves energy savings and satisfies individual rationality simultaneously compared with the conventional schemes. Finally, we identify and discuss open directions on how several emerging technologies are combined with the sustainable green Metaverse.
Generative adversarial networks (GANs) have been extensively studied in the past few years. Arguably their most significant impact has been in the area of computer vision where great advances have been made in challenges such as plausible image generation, image-to-image translation, facial attribute manipulation and similar domains. Despite the significant successes achieved to date, applying GANs to real-world problems still poses significant challenges, three of which we focus on here. These are: (1) the generation of high quality images, (2) diversity of image generation, and (3) stable training. Focusing on the degree to which popular GAN technologies have made progress against these challenges, we provide a detailed review of the state of the art in GAN-related research in the published scientific literature. We further structure this review through a convenient taxonomy we have adopted based on variations in GAN architectures and loss functions. While several reviews for GANs have been presented to date, none have considered the status of this field based on their progress towards addressing practical challenges relevant to computer vision. Accordingly, we review and critically discuss the most popular architecture-variant, and loss-variant GANs, for tackling these challenges. Our objective is to provide an overview as well as a critical analysis of the status of GAN research in terms of relevant progress towards important computer vision application requirements. As we do this we also discuss the most compelling applications in computer vision in which GANs have demonstrated considerable success along with some suggestions for future research directions. Code related to GAN-variants studied in this work is summarized on //github.com/sheqi/GAN_Review.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
Convolutional networks (ConvNets) have achieved great successes in various challenging vision tasks. However, the performance of ConvNets would degrade when encountering the domain shift. The domain adaptation is more significant while challenging in the field of biomedical image analysis, where cross-modality data have largely different distributions. Given that annotating the medical data is especially expensive, the supervised transfer learning approaches are not quite optimal. In this paper, we propose an unsupervised domain adaptation framework with adversarial learning for cross-modality biomedical image segmentations. Specifically, our model is based on a dilated fully convolutional network for pixel-wise prediction. Moreover, we build a plug-and-play domain adaptation module (DAM) to map the target input to features which are aligned with source domain feature space. A domain critic module (DCM) is set up for discriminating the feature space of both domains. We optimize the DAM and DCM via an adversarial loss without using any target domain label. Our proposed method is validated by adapting a ConvNet trained with MRI images to unpaired CT data for cardiac structures segmentations, and achieved very promising results.
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191