A Spatio-Temporal Graph Convolutional Network Model for Internet of Medical Things (IoMT)

Human action recognition is a challenging computer vision task and many efforts have been made to improve the performance. Most previous work has concentrated on the hand-crafted features or spatial-temporal features learned from multiple contiguous frames. In this paper, we present a dual-channel model to decouple the spatial and temporal feature extraction. More specifically, we propose to capture the complementary static form information from single frame and dynamic motion information from multi-frame differences in two separate channels. In both channels we use two stacked classical subspace networks to learn hierarchical representations, which are subsequently fused for action recognition. Our model is trained and evaluated on three typical benchmarks: KTH, UCF and Hollywood2 datasets. The experimental results illustrate that our approach achieves comparable performances to the state-of-the-art methods. In addition, both feature analysis and control experiments are also carried out to demonstrate the effectiveness of the proposed approach for feature extraction and thereby action recognition.

Recently, extensive research into healthcare services and their technological advancements is being carried out globally. The Internet of Things (IoT) has proven to be a predominantly potential candidate in these advancements. IoT supports infrastructure development in connecting a wide range of medical devices, sensors, and health practitioners in order to ensure the best medical treatment for patients in both cities and remote places. This has enabled the IoT to provide major support in medical application, giving rise to assisted healthcare facilities. The IoT ecosystem has a complicated architecture, with several components interacting and an evolving variety of applications for users. This is a comprehensive and interdependent system that involves real-time data analysis, interconnections of device, data transfers, and analysis. The IoT creates a connected ecosystem developed from several intelligent systems that integrates respondents with machines and allows for statistics decision making. A network of interconnected devices that perceive vital data related to medical conditions of patients in real time is referred to as the Internet of Medical Things (IoMT), a healthcare application of IoT technology. Sensors used for sensing real-time data related to monitoring temperature, blood pressure levels, heartbeat levels, specialized signal converters, and communication interfaces can be added to existing medical facilities to turn them into IoMT devices. IoMT can be used to create wearable devices, home-care and personal-care medical devices, and mobile healthcare apps, along with creating communication with medical specialists in a given area. The IoMT system’s challenges and ecosystem interface requirements are also a matter of concern considering the complexity of the systems. This study offers a comprehensive evaluation of the various domains of use of IoMT, as well as its future scope and challenges. Recent advances in sensor technology, networks, cloud storage and processing, mobility, and big data analytics have made it possible to create affordable smart medical devices and a connected healthcare environment.

Internet of things (IoT) becomes the most popular term in the recent advances in Healthcare devices. The healthcare data in the IoT process and structure is very sensitive and critical in terms of healthy and technical considerations. Outlier detection approaches are considered as principal tool or stage of any IoT system and are mainly categorized in statistical and probabilistic, clustering and classification-based outlier detection. Recently, fuzzy logic (FL) system is used in ensemble and cascade systems with other ML-based tools to enhance outlier detection performance but its limitation involves the false detection of outliers. In this paper, we propose a fuzzy logic system that uses the anomaly score of each point using local outlier factor (LOF), connectivity-based outlier factor (COF) and generalized LOF to eliminate the confusion in classifying points as outliers or inliers. Regarding human activity recognition (HAR) dataset, the FL achieved a value of 98.2 %. Compared to the performance of LOF, COF, and GLOF individually, the accuracy increased slightly, but the increase in precision and recall indicates an increase in correctly classified data and that neither true nor abnormal data is classified wrongly. The results show the increase in precision and recall which indicates an increase in correctly classified data. Thus, it can be confirmed that fuzzy logic with input of scores achieved the desired goal in terms of mitigating cases of false detection of anomalous data. By comparing the proposed ensemble of fuzzy logic and different types of local density scores in this study, the outcomes of fuzzy logic presents a new way of elaborating or fusing the different tools of the same purpose to enhance detection performance

Human motion detection and activity recognition are becoming vital for the applications in smart homes. Traditional Human Activity Recognition (HAR) mechanisms use special devices to track human motions, such as cameras (vision-based) and various types of sensors (sensor-based). These mechanisms are applied in different applications, such as home security, Human–Computer Interaction (HCI), gaming, and healthcare. However, traditional HAR methods require heavy installation, and can only work under strict conditions. Recently, wireless signals have been utilized to track human motion and HAR in indoor environments. The motion of an object in the test environment causes fluctuations and changes in the Wi-Fi signal reflections at the receiver, which result in variations in received signals. These fluctuations can be used to track object (i.e., a human) motion in indoor environments. This phenomenon can be improved and leveraged in the future to improve the internet of things (IoT) and smart home devices. The main Wi-Fi sensing methods can be broadly categorized as Received Signal Strength Indicator (RSSI), Wi-Fi radar (by using Software Defined Radio (SDR)) and Channel State Information (CSI). CSI and RSSI can be considered as device-free mechanisms because they do not require cumbersome installation, whereas the Wi-Fi radar mechanism requires special devices (i.e., Universal Software Radio Peripheral (USRP)). Recent studies demonstrate that CSI outperforms RSSI in sensing accuracy due to its stability and rich information. This paper presents a comprehensive survey of recent advances in the CSI-based sensing mechanism and illustrates the drawbacks, discusses challenges, and presents some suggestions for the future of device-free sensing technology.

Developments in information and communication technologies have led to the wider usage of Internet of Things (IoT). In the modern health care applications, the usage of IoT technologies brings physicians and patients together for automated and intelligent daily activity monitoring for elderly people. Mobile devices and wearable body sensors are gradually implemented for the monitoring of personal health care and wellbeing. One of the main technologies of IoT improvements in healthcare monitoring system is the wearable sensor technology. Furthermore, integration of IoT in healthcare has led to initiate smart applications such as mobile healthcare (m-Healthcare) and intelligent healthcare monitoring systems. In this study an intelligent m-healthcare system based on IoT technology is presented to provide pervasive human activity recognition by using data mining techniques. In this paper, we present a user-dependent data mining approach for off-line human activity classification and a robust and precise human activity recognition model is developed based on IoT technology. The proposed model utilizes the dataset contains body motion and vital signs recordings for ten volunteers of diverse profile while performing 12 physical activities for human activity recognition purpose. Results show that the proposed system is superior in performance with 99.89 % accuracy and is highly effective, robust and reliable in delivering m-Healthcare services during different activities.

SummaryWith the development of Internet of Things (IoT)‐related technologies and artificial intelligence (AI) technologies, various IoT services are becoming more intelligent, and their use range is increasing and diversifying. IoT hardware and IoT software must support AI‐related functions to provide an intelligent IoT service. In general, IoT devices powered by batteries have limited computing performance when compared to general computing environments. Therefore, it is essential to provide AI‐related functions at low power in IoT devices to implement and offer various intelligent services. Neuromorphic computing devices or neuromorphic computing architectures can operate with low power energy consumption. If applied to IoT devices, AI‐related functions can be implemented in a resource‐constrained IoT device environment. The proposed neuromorphic architecture abstraction (NAA) model dynamically selects the proper neuromorphic architecture by comparing the parameter size of a given SNN model. It also considers the specifications and error probability of the available neuromorphic architecture. We also implement the proposed model in a real IoT computing environment and show that the proposed NAA model and dynamic selection scheme can reduce the execution time for training and inferencing. It reduces the training and inferencing time of a given model compared with the method of randomly specifying the neuromorphic architecture.

The recognition of human activities using vision-based techniques has become a crucial research field in video analytics. Over the last decade, there have been numerous advancements in deep learning algorithms aimed at accurately detecting complex human actions in video streams. While these algorithms have demonstrated impressive performance in activity recognition, they often exhibit a bias towards either model performance or computational efficiency. This biased trade-off between robustness and efficiency poses challenges when addressing complex human activity recognition problems. To address this issue, this paper presents a computationally efficient yet robust approach, exploiting saliency-aware spatial and temporal features for human action recognition in videos. To achieve effective representation of human actions, we propose an efficient approach called the dual-attentional Residual 3D Convolutional Neural Network (DA-R3DCNN). Our proposed method utilizes a unified channel-spatial attention mechanism, allowing it to efficiently extract significant human-centric features from video frames. By combining dual channel-spatial attention layers with residual 3D convolution layers, the network becomes more discerning in capturing spatial receptive fields containing objects within the feature maps. To assess the effectiveness and robustness of our proposed method, we have conducted extensive experiments on four well-established benchmark datasets for human action recognition. The quantitative results obtained validate the efficiency of our method, showcasing significant improvements in accuracy of up to 11% as compared to state-of-the-art human action recognition methods. Additionally, our evaluation of inference time reveals that the proposed method achieves up to a 74× improvement in frames per second (FPS) compared to existing approaches, thus showing the suitability and effectiveness of the proposed DA-R3DCNN for real-time human activity recognition.

Chapter 2 - AIoMT artificial intelligence (AI) and Internet of Medical Things (IoMT): applications, challenges, and future trends

As the development of Internet of Things (IoT) technology has enabled various forms of intelligent services to be provided personalized intelligent services are provided for each person based on the data collected from IoT devices through P2P networking. Intelligent IoT services are gradually expanding. However, there can be various security risks in the devices that make up IoT networking. Untrusted devices can affect personalized IoT services by distorting personal information in analyzing the collected data. Therefore, services by the untrusted devices should be restricted. In this paper, the reliability is defined as the familiarity score, which is determined by the connection experience of the devices in a P2P IoT network. The IoT network composed of devices with high familiarity scores can be defined as a trusted area. In the trusted area, data generated by all devices is used to create knowledge for personalized intelligent services for users. In contrast, personalized intelligent services in untrusted area are restricted. Data generated by untrusted devices is classified by a learning algorithm such as logistic regression; thus, bad data is blocked by a gateway to avoid information distortion in data analysis for personalized intelligent services. The proposed method provides a trusted networking environment to IoT service users and protects data integrity. Thus, it can improve the user’s quality of experience (QoE) for personalized intelligent services. The proposed approach is evaluated by computer simulation and its superiority is validated.

There have been many attempts to predict new markets, including a new market for internet of things (IoT)-based healthcare and the IoT platform’s ability to offer a variety of applications. It is anticipated that the market for these devices will continue to grow as the healthcare sector undergoes fast expansion. IoT can measure a user’s kinetic data (calorie consumption, distance, number of steps, etc.) using wearable healthcare equipment. Most of the recent top research on IoT-based healthcare wearable devices (IWHDs) has, up to this point, concentrated on potential users. The medical industry and healthcare are being quickly changed by the use and adoption of wearable healthcare devices. This study intended to uncover the mediating impacts of “perceived ease of use”, “perceived usefulness”, and “community immersion” on the interactions between influencing factors (personalization, service convenience, interactivity), and the intention to utilize IHWDs. The moderating role of a consumer’s innovativeness in the influence link between IHWD features on perceived ease of use and perceived usefulness was also examined. The study found that personalization has a direct (+) impact on usage intention. Through this, it would be feasible to raise the intention of wearable medical devices being accepted if customized benefits that are thoroughly examined just for individuals are supplied. The association between personalization and continued use intention was shown to be partially mediated by perceived utility and community immersion. Additionally, the association between interactivity and continued use intention, was fully mediated by perceived usefulness and community immersion. By analyzing the elements influencing the usage intention of wearable healthcare devices, this study offers a marketing plan to increase the number of users. The internet of medical things (IoMT) sector has had compound growth of approximately 26% from 2018 to 2021, which is a remarkable accomplishment. The effectiveness of factors affecting IoT usage was examined in this study when applied to the actual IoT industry. First, patients with diabetes who previously had to check their blood sugar levels through a blood test can now check it through lifestyle management and steady glucose monitoring through IoMT glucose monitoring when the convenience and individuality of the service are improved. So far, 10% of all Americans have benefited from this device. Second, as an illustration of interactivity, an IoMT-connected inhaler used to assist asthma sufferers with breathing, notifies the user when the inhaler is left at home and reminds them of appropriate times to use the device. This subsequently resulted in saving 1 life out of every 3 deaths. In addition, the findings of this study may also provide a turning point for the design and development of cutting-edge IoT-based healthcare goods and services.

An increase in life expectancy is leading to an aging society, where gradual degradation in physical/cognitive health could result in fall injuries, cardiovascular, neurological/psychological problems, or a sedentary lifestyle. Sensor-based human activity recognition (HAR) is found to be a potential assistive technology in this context to improve the quality of life of an aging society. This chapter presents the state of the art and future trends of Internet of Things (IoT)-enabled sensor data-based Human Activity Recognition (HAR) systems, where machine learning (ML)/deep learning (DL) is used to classify human actions in the context of healthcare applications. In particular, the impact of IoT on the healthcare industry is so immense that a dedicated specialization, termed as Internet of Healthcare Things (IoHT), has emerged. Smart healthcare systems are equipped with different categories of sensors (wearable, wireless, and ambient). The huge amount of sensor data acquired by IoHT sensors allows for performing accurate HAR. The HAR involves detection/classification problems, e.g. fall detection and seizer detection, where ML is used extensively, at its heart. A lot of ML/DL techniques are being used in HAR including support vector machine (SVM), artificial neural network (ANN), recurrent neural network (RNN), convolutional neural network (CNN), deep neural network (DNN), long short-term memory (LSTM), etc. However, there are a few special aspects of HAR sensor data that make it difficult to handle. Involved research is still being pursued across the globe to solve these problems.KeywordsIoTIoHTHealth careHARSensorMachine learning (ML)Deep learning (DL)

The Internet of Things (IoT) enabled technologies to have proliferated due to their abilities to capture and exchange quality information. This empirical study aims to investigate the factors influencing the intention to use IoT services in healthcare by young physicians. An integrated model based on the theory of planned behaviour (TPB) and diffusion of innovations (DOI) theories are drawn upon and analyzed through a Structural Equation Modelling (SEM) with importance-performance map analysis (IPMA). Data were collected through a structured survey questionnaire. The results indicated that behavioural intention to use IoT in healthcare services vastly affected by the attitude and value co-creation. Attitude was found to be a principal determinant followed by the relative advantage towards behavioural intention to use IoT services. The novelty of this empirical study is that the proposed integrated model provides a meaningful application of the young physicians’ intention to use IoT in healthcare in developing countries.

Ultra-wideband radar-based penetrating detection and recognition of human activities has become a focus on remote sensing in various military applications in recent years, such as urban warfare, hostage rescue, and earthquake post-disaster rescue. However, an excellent micro-Doppler signature (MDS) extracting method of human motion with high time-frequency resolution, outstanding anti-interference ability, and extensive adaptability, which aims to provide favorable and more detailed features for human activity recognition and classification, especially in the non-free space detection environment, is in great urgency. To cope with the issue, a multiple Hilbert-Huang transform (MHHT) method is proposed for high-resolution time-frequency analysis of finer-grained human activity MDS hidden in ultra-wideband (UWB) radar echoes during the through-wall detection environment. Based on the improved HHT with effective intrinsic mode function (IMF) selection according to the cosine similarity (CS) principle, the improved HHT is applied to each channel signal in the effective channel scope of the UWB radar signal and then integrated along the range direction. The activities of swinging one or two arms while standing at a spot 3 m from a wall were used to validate the abilities of the proposed method for extracting and separating the MDS of different moving body structures with a high time-frequency resolution. Simultaneously, the corresponding relationship between the frequency components in MHHT-based spectra and structures of the moving human body was demonstrated according to the radar Doppler principle combined with the principle of human body kinematics. Moreover, six common finer-grained human activities and a piaffe at different ranges under the through-wall detection environment were exploited to confirm the adaptability of the novel method for different activities and pre-eminent anti-interference ability under a low signal-noise-clutter ratio (SNCR) environment, which is critical for remote sensing in various military application, such as urban warfare, hostage rescue, earthquake post-disaster rescue.

Purpose: The purpose of this study is to discern the prospects and challenges of integrating Internet of Things (IoT) into the public healthcare sector of Bangladesh. This is timely because the present public healthcare status of the country needs dire improvement. Hence, this study explores the future scope of IoT-based public healthcare systems to be introduced to the Directorate General of Health Services (DGHS) of Bangladesh henceforth recommends how the country can integrate the implementation of this technology to deliver better public healthcare services to its population. Methodology: The authors reviewed extensively literature from several reputed sources to identify the current public healthcare conditions, as well as the benefits and impediments of IoT-based public healthcare system in Bangladesh. Based on the searches pertaining to the data base, this study then outlines appropriate future scopes of IoT in the public healthcare of Bangladesh. Findings: This research identified major impediments such as lack of infrastructure, low motivation, awareness and acceptance as well as poor healthcare startups prevalent in the public health services of Bangladesh. To surmount the inefficiencies of the current services, the authors deliberated how IoT based public healthcare system could foster better monitoring; management and rehabilitation thereby improve the overall Bangladesh’s public healthcare system. Practical Implications: IoT healthcare organizations can also use technology to improve patient outcomes and increase efficiencies, which will lower the cost of treatment, reduce death rates and make it possible to give public healthcare to people who live in rural areas. Originality/Value: The researchers of this study are confident that the findings of this study will benefit other researchers, policymakers, healthcare service providers/designers and professionals to realize the potentials of IoT-based public healthcare system that could overcome the challenges faced and finally could deliver sound public healthcare facilities and services for Bangladeshis in the near future. Limitations: In the future, we plan to develop the Central Repository of patient database system using blockchain technology.

The Internet of Things (IoT) revolution is redesigning modern city, home, health care and industry services and applications with promising technological, economic, and social prospects. The potential of the emerging Internet of Things technology has been presented in this chapter with focus on current and probable applications in the healthcare domain. The Internet of Things will bring seamless ‘anytime, anywhere’ personalized healthcare and monitoring over fast reliable and secure networks. Big data and IoT are topical emerging technologies that attract focus from several researchers and engineers to develop the next generation of smarter connected devices/products. From providing services for creating smart homes to smart cities, the IoT intelligent system offer better solutions, by automating processes, facilitating collaboration, and securely managing information. It will lead to widespread variety of services to more population which in turn will lead to overall lifestyle improvement and seamless connectivity. A collection of interconnected IoT devices in conjunction with machine learning and artificial intelligence is used to perform predictive analysis, diagnosis, remote monitoring, and preventative analysis. Expanding wireless communication technologies and services requires compact antennas operating over a wide range of frequency band such as ISM, UWB and mmWave range. The antennas need to be compact, application specific to support the Internet-of-Things for sensing and onward transmission over the wireless networks. Hence, this chapter also explores the potential of different technologies and state-of-the art techniques for potential, wearable antennas for on-and off-body smart devices.