Search

The enhanced proliferation of connected entities needs a deployment of innovative technologies for the next generation wireless networks. One of the critical concerns, however, is the spectrum scarcity, due to the unprecedented broadcast penetration rate nowadays. Based on this, visible light communication (VLC) has recently emerged as a viable solution to secure high-speed communications. VLC, a high data rate communication technology, has proven its stature as a promising complementary to its radio frequency (RF) counterpart. VLC is a cost-effective, energy-efficient, and secure technology that exploits the current infrastructure, specifically within indoor and underwater environments. Yet, despite their appealing capabilities, VLC systems face several limitations which constraint their potentials such as LED's limited bandwidth, dimming, flickering, line-of-sight (LOS) requirement, impact of harsh weather conditions, noise, interference, shadowing, transceiver alignment, signal decoding complexity, and mobility issue. Consequently, non-orthogonal multiple access (NOMA) has been considered an effective technique to circumvent these shortcomings. The NOMA scheme has emerged as a revolutionary paradigm to address the shortcomings of VLC systems. The potentials of NOMA are to increase the number of users, system's capacity, massive connectivity, and enhance the spectrum and energy efficiency in future communication scenarios. Motivated by this, the presented study offers an overview of NOMA-based VLC systems. This article provides a broad scope of existing research activities of NOMA-based VLC systems. This article aims to provide firsthand knowledge of the prominence of NOMA and VLC and surveys several NOMA-enabled VLC systems. We briefly highlight the potential and capabilities of NOMA-based VLC systems. In addition, we outline the integration of such systems with several emerging technologies such as intelligent reflecting surfaces (IRS), orthogonal frequency division multiplexing (OFDM), multiple-input and multiple-output (MIMO) and unmanned aerial vehicles (UAVs). Furthermore, we focus on NOMA-based hybrid RF/VLC networks and discuss the role of machine learning (ML) tools and physical layer security (PLS) in this domain. In addition, this study also highlights diverse and significant technical hindrances prevailing in NOMA-based VLC systems. We highlight future research directions, along with provided insights that are envisioned to be helpful towards the effective practical deployment of such systems. In a nutshell, this review highlights the existing and ongoing research activities for NOMA-based VLC systems, which will provide sufficient guidelines for research communities working in this domain and it will pave the way for successful deployment of these systems. [ABSTRACT FROM AUTHOR]

Artificial intelligence plays an essential role in diagnosing lung cancer. Lung cancer is notoriously difficult to diagnose until it has progressed to a late stage, making it a leading cause of cancer-related mortality. Lung cancer is fatal if not treated early, making this a significant issue. Initial diagnosis of malignant nodules is often made using chest radiography (X-ray) and computed tomography (CT) scans; nevertheless, the possibility of benign nodules leads to wrong choices. In their first phases, benign and malignant nodules seem very similar. Additionally, radiologists have a hard time viewing and categorizing lung abnormalities. Lung cancer screenings performed by radiologists are often performed with the use of computer-aided diagnostic technologies. Computer scientists have presented many methods for identifying lung cancer in recent years. Low-quality images compromise the segmentation process, rendering traditional lung cancer prediction algorithms inaccurate. This article suggests a highly effective strategy for identifying and categorizing lung cancer. Noise in the pictures was reduced using a weighted filter, and the improved Gray Wolf Optimization method was performed before segmentation with watershed modification and dilation operations. We used InceptionNet-V3 to classify lung cancer into three groups, and it performed well compared to prior studies: 98.96% accuracy, 94.74% specificity, as well as 100% sensitivity. [ABSTRACT FROM AUTHOR]

An efficient feature extraction method for two classes of electroencephalography (EEG) is demonstrated using Common Spatial Patterns (CSP) with optimal spatial filters. However, the effects of artifacts and non-stationary uncertainty are more pronounced when CSP filtering is used. Furthermore, traditional CSP methods lack frequency domain information and require many input channels. Therefore, to overcome this shortcoming, a feature extraction method based on Online Recursive Independent Component Analysis (ORICA)-CSP is proposed. For EEG-based brain—computer interfaces (BCIs), especially online and real-time BCIs, the most widely used classifiers used to be linear discriminant analysis (LDA) and support vector machines (SVM). Previous evaluations clearly show that SVMs generally outperform other classifiers in terms of performance. In this case, Adaptive Support Vector Machine (A-SVM) is used for classification together with the ORICA-CSP method. The results are promising, and the experiments are performed on EEG data of 4 classes' motor images, namely Dataset 2a of BCI Competition IV. [ABSTRACT FROM AUTHOR]

Human physical activity recognition from inertial sensors is shown to be a successful approach for monitoring elderly individuals and children in indoor and outdoor environments. As a result, researchers have shown significant interest in developing state-of-the-art machine learning methods capable of utilizing inertial sensor data and providing key decision support in different scenarios. This paper analyzes data-driven techniques for recognizing human daily living activities. Therefore, to improve the recognition and classification of human physical activities (for example, walking, drinking, and running), we introduced a model that integrates data preprocessing methods (such as denoising) along with major domain features (such as time, frequency, wavelet, and time–frequency features). Following that, stochastic gradient descent (SGD) is used to improve the performance of the extracted features. The selected features are catered to the random forest classifier to detect and monitor human physical activities. Additionally, the proposed HPAR system was evaluated on five benchmark datasets, namely the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE databases. The experimental results show that the HPAR system outperformed the present state-of-the-art methods with recognition rates of 90.18%, 91.25%, 91.83%, 90.46%, and 92.16% from the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE datasets, respectively. The proposed HPAR model has potential applications in healthcare, gaming, smart homes, security, and surveillance. [ABSTRACT FROM AUTHOR]

Network slicing (NS) is one of the most prominent next-generation wireless cellular technology use cases, promising to unlock the core benefits of 5G network architecture by allowing communication service providers (CSPs) and operators to construct scalable and customized logical networks. This, in turn, enables telcos to reach the full potential of their infrastructure by offering customers tailored networking solutions that meet their specific needs, which is critical in an era where no two businesses have the same requirements. This article presents a commercial overview of NS, as well as the need for a slicing automation and orchestration framework. Furthermore, it will address the current NS project objectives along with the complex functional execution of NS code flow. A summary of activities in important standards development groups and industrial forums relevant to artificial intelligence (AI) and machine learning (ML) is also provided. Finally, we identify various open research problems and potential answers to provide future guidance. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) seem to be the most efficient way of achieving the intended aerial tasks, according to recent improvements. Various researchers from across the world have studied a variety of UAV formations and path planning methodologies. However, when unexpected obstacles arise during a collective flight, path planning might get complicated. The study needs to employ hybrid algorithms of bio-inspired computations to address path planning issues with more stability and speed. In this article, two hybrid models of Ant Colony Optimization were compared with respect to convergence time, i.e., the Max-Min Ant Colony Optimization approach in conjunction with the Differential Evolution and Cauchy mutation operators. Each algorithm was run on a UAV and traveled a predetermined path to evaluate its approach. In terms of the route taken and convergence time, the simulation results suggest that the MMACO-DE technique outperforms the MMACO-CM approach. [ABSTRACT FROM AUTHOR]

Alzheimer's Disease (AD) is a health apprehension of significant proportions that is negatively impacting the ageing population globally. It is characterized by neuronal loss and the formation of structures such as neurofibrillary tangles and amyloid plaques in the early as well as later stages of the disease. Neuroimaging modalities are routinely used in clinical practice to capture brain alterations associated with AD. On the other hand, deep learning methods are routinely used to recognize patterns in underlying data distributions effectively. This work uses Convolutional Neural Network (CNN) architectures in both 2D and 3D domains to classify the initial stages of AD into AD, Mild Cognitive Impairment (MCI) and Normal Control (NC) classes using the positron emission tomography neuroimaging modality deploying data augmentation in a random zoomed in/out scheme. We used novel concepts such as the blurring before subsampling principle and distant domain transfer learning to build 2D CNN architectures. We performed three binaries, that is, AD/NC, AD/MCI, MCI/NC and one multiclass classification task AD/NC/MCI. The statistical comparison revealed that 3D-CNN architecture performed the best achieving an accuracy of 89.21% on AD/NC, 71.70% on AD/MCI, 62.25% on NC/MCI and 59.73% on AD/NC/MCI classification tasks using a five-fold cross-validation hyperparameter selection approach. Data augmentation helps in achieving superior performance on the multiclass classification task. The obtained results support the application of deep learning models towards early recognition of AD. [ABSTRACT FROM AUTHOR]

Biometrics is the term for measuring human characteristics. If the term is divided into two parts, bio means life, and metric means measurement. The measurement of humans through different computational methods is performed to authorize a person. This measurement can be performed via a single biometric or by using a combination of different biometric traits. The combination of multiple biometrics is termed biometric fusion. It provides a reliable and secure authentication of a person at a higher accuracy. It has been introduced in the UIDIA framework in India (AADHAR: Association for Development and Health Action in Rural) and in different nations to figure out which biometric characteristics are suitable enough to authenticate the human identity. Fusion in biometric frameworks, especially FKP (finger–knuckle print) and iris, demonstrated to be a solid multimodal as a secure framework. The proposed approach demonstrates a proficient and strong multimodal biometric framework that utilizes FKP and iris as biometric modalities for authentication, utilizing scale-invariant feature transform (SIFT) and speeded up robust features (SURF). Log Gabor wavelet is utilized to extricate the iris feature set. From the extracted region, features are computed using principal component analysis (PCA). Both biometric modalities, FKP and iris, are combined at the match score level. The matching is performed using a neuro-fuzzy neural network classifier. The execution and accuracy of the proposed framework are tested on the open database Poly-U, CASIA, and an accuracy of 99.68% is achieved. The accuracy is higher compared to a single biometric. The neuro-fuzzy approach is also tested in comparison to other classifiers, and the accuracy is 98%. Therefore, the fusion mechanism implemented using a neuro-fuzzy classifier provides the best accuracy compared to other classifiers. The framework is implemented in MATLAB 7.10. [ABSTRACT FROM AUTHOR]

The proliferation of Internet-of-Things (IoT) technology and its reliance on the license-free Industrial, Scientific, and Medical (ISM) bands have rendered radio spectrum scarce. The IoT can nevertheless obtain great advantage from Cognitive Radio (CR) technology for efficient use of a spectrum, to be implemented in IEEE 802.11af-based primary networks. However, such networks require a geolocation database and a centralized architecture to communicate white space information on channels. On the other hand, in spectrum sensing, CR presents various challenges such as the Hidden Primary Terminal (HPT) problem. To this end, we focus on the most recently released standard, i.e., IEEE 802.11ah, in which IoT stations can first be classified into multiple groups to reduce collisions and then they can periodically access the channel. Therein, both services are similarly supported by a centralized server that requires signaling overhead to control the groups of stations. In addition, more regroupings are required over time due to the frequent variations in the number of participating stations, which leads to more overhead. In this paper, we propose a new Multiple Access Control (MAC) protocol for CR-based IEEE 802.11ah systems, called Restricted Access with Collision and Interference Resolution (RACIR).We introduce a decentralized group split algorithm that distributes the participating stations into multiple groups based on a probabilistic estimation in order to resolve collisions. Furthermore, we propose a decentralized channel access procedure that avoids the HPT problem and resolves interference with the incumbent receiver. We analyze the performance of our proposed MAC protocol in terms of normalized throughput, packet delay and energy consumption with the Markov model and analytic expressions. The results are quite promising, which makes the RACIR protocol a strong candidate for the CR-based IoT environment. [ABSTRACT FROM AUTHOR]

Fitness and sport have drawn significant attention in wearable and persuasive computing. Physical activities are worthwhile for health, well-being, improved fitness levels, lower mental pressure and tension levels. Nonetheless, during high-power and commanding workouts, there is a high likelihood that physical fitness is seriously influenced. Jarring motions and improper posture during workouts can lead to temporary or permanent disability. With the advent of technological advances, activity acknowledgment dependent on wearable sensors has pulled in countless studies. Still, a fully portable smart fitness suite is not industrialized, which is the central need of today's time, especially in the Covid-19 pandemic. Considering the effectiveness of this issue, we proposed a fully portable smart fitness suite for the household to carry on their routine exercises without any physical gym trainer and gym environment. The proposed system considers two exercises, i.e., T-bar and bicep curl with the assistance of the virtual real-time android application, acting as a gym trainer overall. The proposed fitness suite is embedded with a gyroscope and EMG sensory modules for performing the above two exercises. It provided alerts on unhealthy, wrong posture movements over an android app and is guided to the best possible posture based on sensor values. The KNN classification model is used for prediction and guidance for the user while performing a particular exercise with the help of an android application-based virtual gym trainer through a text-to-speech module. The proposed system attained 89% accuracy, which is quite effective with portability and a virtually assisted gym trainer feature. [ABSTRACT FROM AUTHOR]

The integration of medical signal processing capabilities and advanced sensors into Internet of Things (IoT) devices plays a key role in providing comfort and convenience to human lives. As the number of patients is increasing gradually, providing healthcare facilities to each patient, particularly to the patients located in remote regions, not only has become challenging but also results in several issues, such as: (i) increase in workload on paramedics, (ii) wastage of time, and (iii) accommodation of patients. Therefore, the design of smart healthcare systems has become an important area of research to overcome these above-mentioned issues. Several healthcare applications have been designed using wireless sensor networks (WSNs), cloud computing, and fog computing. Most of the e-healthcare applications are designed using the cloud computing paradigm. Cloud-based architecture introduces high latency while processing huge amounts of data, thus restricting the large-scale implementation of latency-sensitive e-healthcare applications. Fog computing architecture offers processing and storage resources near to the edge of the network, thus, designing e-healthcare applications using the fog computing paradigm is of interest to meet the low latency requirement of such applications. Patients that are minors or are in intensive care units (ICUs) are unable to self-report their pain conditions. The remote healthcare monitoring applications deploy IoT devices with bio-sensors capable of sensing surface electromyogram (sEMG) and electrocardiogram (ECG) signals to monitor the pain condition of such patients. In this article, fog computing architecture is proposed for deploying a remote pain monitoring system. The key motivation for adopting the fog paradigm in our proposed approach is to reduce latency and network consumption. To validate the effectiveness of the proposed approach in minimizing delay and network utilization, simulations were carried out in iFogSim and the results were compared with the cloud-based systems. The results of the simulations carried out in this research indicate that a reduction in both latency and network consumption can be achieved by adopting the proposed approach for implementing a remote pain monitoring system. [ABSTRACT FROM AUTHOR]

As the expenses of medical care administrations rise and medical services experts are becoming rare, it is up to medical services organizations and institutes to consider the implementation of medical Health Information Technology (HIT) innovation frameworks. HIT permits health associations to smooth out their considerable cycles and offer types of assistance in a more productive and financially savvy way. With the rise of Cloud Storage Computing (CSC), an enormous number of associations and undertakings have moved their healthcare data sources to distributed storage. As the information can be mentioned whenever universally, the accessibility of information becomes an urgent need. Nonetheless, outages in cloud storage essentially influence the accessibility level. Like the other basic variables of cloud storage (e.g., reliability quality, performance, security, and protection), availability also directly impacts the data in cloud storage for e-Healthcare systems. In this paper, we systematically review cloud storage mechanisms concerning the healthcare environment. Additionally, in this paper, the state-of-the-art cloud storage mechanisms are critically reviewed for e-Healthcare systems based on their characteristics. In short, this paper summarizes existing literature based on cloud storage and its impact on healthcare, and it likewise helps researchers, medical specialists, and organizations with a solid foundation for future studies in the healthcare environment. [ABSTRACT FROM AUTHOR]

Floor identification plays a key role in multi-story indoor positioning and localization systems. Current floor identification systems rely primarily on Wi-Fi signals and barometric pressure data. Barometric systems require installation of additional standalone sensors to perform floor identification. Wi-Fi systems, on the other hand, are vulnerable to the dynamic environment and adverse effects of path loss, shadowing, and multipath fading. In this paper, we take advantage of a pervasive magnetic field to compensate for the limitations of these systems. We employ smartphone sensors to make the proposed scheme infrastructure free and cost-effective. We use smartphone magnetic sensors to identify the floors in a multi-story building with improved accuracy. Floor identification is performed with user activities of normal walking, call listening, and phone swinging. Various machine learning techniques are leveraged to identify user activities. Extensive experiments are performed to evaluate the proposed magnetic-data-based floor identification scheme. Additionally, the impact of device heterogeneity on floor identification is investigated using Samsung Galaxy S8, LG G6, and LG G7 smartphones. Research results demonstrate that the magnetic floor identification outperforms barometric and Wi-Fi-enabled floor detection techniques. A floor change module is incorporated to further enhance the accuracy of floor identification. [ABSTRACT FROM AUTHOR]

The widespread growth of the Internet-of-Things (IoT) and its dependence on the license-exempt Industrial, Scientific, and Medical (ISM) bands have made spectrum resources scarce. IoT can nonetheless get advantage from the Cognitive Radio (CR) technology to resolve the spectrum shortage issue. Since in CR networks the unlicensed Secondary Users (SUs) can exploit the white spaces in licensed channels of Primary Users (PUs) opportunistically. CR ad hoc networks are more useful in IoT due to ease of installation, low cost, and less complexity. However, CR ad hoc networks are prone to the rendezvous issue and hidden primary terminal problem. Moreover, the available channels in the CR system are not identical, PUs' and SUs' activities can diversify them as well. In this connection, channel selection by SUs is a complex balancing act since the transmission opportunities are space, frequency and time bounded. In this paper, we hence proposed a new Ranked Sense Multiple Access with Collision Avoidance (RSMA/CA) protocol for multichannel CR-based IoT networks. Our proposed RSMA/CA protocol not only resolves the hidden primary terminal problem but also avoids hidden and exposed terminal problems at the same time by mutual spectrum sensing. We suggest a new channel ranking mechanism to rank the available channels based on the long term qualities of the channels, PUs' return rate, and SUs' activities and tailor-made the algorithms in an existing scheme to make the rendezvous process more efficient. We analyze the performance of our proposed RSMA/CA in terms of normalized throughput through the Markov chain model and compared with that of the existing scheme. Simulation results show that our RSMA/CA protocol outperforms the existing scheme due to efficient rendezvous and access mechanisms. [ABSTRACT FROM AUTHOR]

Internet-of-Things (IoT) enabling technologies such as ZigBee, WiFi, 6LowPAN, RFID, Machine-to-Machine, LTE-Advanced, etc. depend on the license-free Industrial Scientific and Medical (ISM) bands for the Internet. The proliferation of IoT devices is not only anticipated to create a huge amount of congestion in the near future, but even now the unlicensed spectrum is not enough in the ISM bands. Towards this end, Cognitive Radio (CR) technology can resolve the spectrum shortage issue since CR users can opportunistically exploit white spaces in licensed channels of the adjacent wireless systems. In CR networks, it is critical to coordinate spectrum access among Secondary Users (SUs) while protecting priority rights of Primary Users (PUs). Therein, SUs need to take good care of hidden PUs in order to avoid harmful interference. Further, a densely deployed CR network can compromise spectrum sensing quality and certainty of the results when a large number of SUs contends to access the same channel. Therefore, based on the vulnerable sensing results, SUs can cause interference to the PUs. In this paper, we first investigate the leading issues and then propose a novel Handshake Sense Multiple Access with Collision Avoidance (HSMA/CA) protocol for CR-based IoT networks. Our proposed HSMA/CA scheme resolves hidden primary terminal problem and maintains sufficient priority rights to PUs in a densely distributed network. In addition, we optimize the spectrum sensing period to maximize the system performance by maintaining peculiarities in the sensing operation like false alarm and misdetection. To evaluate the performance of HSMA/CA, we have analyzed the protocol through the Markov chain model in terms of throughput and verify its accuracy by simulations. Simulation results show that our scheme is suitable for non-collaborative densely deployed CR-based IoT networks. [ABSTRACT FROM AUTHOR]

Auction theory has found vital application in cognitive radio to relieve spectrum scarcity by redistributing idle channels to those who value them most. However, countries have been slow to introduce spectrum auctions in the secondary market. This could be in part because a number of substantial conflicts could emerge for leasing the spectrum at the micro level. These representative conflicts include the lack of legislation, interference management, setting a reasonable price, etc. In addition, the heterogeneous nature of the spectrum precludes the true evaluation of non-identical channels. The information abstracted from the initial activity in terms of price paid for specific channels may not be a useful indicator for the valuation of another channel. Therefore, auction mechanisms to efficiently redistribute idle channels in the secondary market are of vital interest. In this paper, we first investigate such leading conflicts and then propose a novel Adaptive and Economically-Robust spectrum slot Group-selling scheme (AERG), for cognitive radio-based networks such as IoT, 5G and LTE-Advanced. This scheme enables group-selling behavior among the primary users to collectively sell their uplink slots that are individually not attractive to the buyers due to the auction overhead. AERG is based on two single-round sealed-bid reverse-auction mechanisms accomplished in three phases. In the first phase, participants adapt asks and bids to fairly evaluate uplink slots considering the dynamics of spectrum trading such as space and time. In the second phase, an inner-auction in each primary network is conducted to collect asks on group slots, and then, an outer-auction is held between primary and secondary networks. In the third phase, the winning primary network declares the winners of the inner-auction that can evenly share the revenue of the slots. Simulation results and logical proofs verify that AERG satisfies economic properties such as budget balance, truthfulness and individual rationality and improves the utilities of the participants. [ABSTRACT FROM AUTHOR]