This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera. Existing non-contact breath assessments achieve satisfactory results under restricted conditions when human body stays relatively still. When someone moves forward, the breath signals detected by depth camera are hidden within signals of trunk displacement and deformation, and the signal length is short due to the short stay time, posing great challenges for us to establish models. To over-come these challenges, multiple region of interests (ROIs) based signal extraction and selection method is proposed to automatically obtain the signal informative to breath from depth video. Subsequently, graph signal analysis (GSA) is adopted as a spatial-temporal filter to wipe the components unrelated to breath. Finally, a classifier for identifying deep breath is established based on the selected breath-informative signal. In validation experiments, the proposed approach outperforms the comparative methods with the accuracy, precision, recall and F1 of 75.5%, 76.2%, 75.0% and 75.2%, respectively. This system can be extended to public places to provide timely and ubiquitous help for those who may have or are going through physical or mental trouble.

This paper presents a low-cost and unobtrusive intelligent respiratory monitoring system. To achieve low-cost and remote measurement of respiratory signal, an RGB camera collaborated with marker tracking is used as data acquisition sensor, and a Raspberry Pi is used as data processing platform. To overcome challenges in actual applications, the signal processing algorithms are designed for removing sudden body movements and smoothing the raw signal. To discover more specific information in the respiratory signal, respiratory rate is estimated by a translational cross point algorithm, and respiratory pattern is identified by recurrent neural network. Finally, the obtained decision-making information and some original information are sent to user's smartphone via a cloud service platform. For estimating respiratory rate, the Bland-Altman plot demonstrates the satisfactory results with agreement ranges of -0.13 ± 5.85 bpm. With respect to the classification of breathing patterns, the results validate that the system has the good performance with the accuracy, precision, recall, and F1 of 92.5%, 92.5%, 93.3%, and 92.9%, respectively. This work may contribute to the development of low-cost and non-contact respiratory monitoring products specific to home or work health care.

The aim of this study is to develop an affordable and remote intelligent respiratory monitoring system. To achieve low-cost and remote measurement of respiratory signal, an RGB camera collaborated with marker tracking is used as a data acquisition sensor, and a Raspberry Pi is used as a data processing platform. To overcome challenges in actual applications, the signal processing algorithms are designed for removing sudden body movements and smoothing the raw signal. Subsequently, respiratory rate (RR) is estimated by a translational cross-point algorithm, and the respiratory pattern is identified by the recurrent neural network. For estimating RR, the translational cross-point algorithm performs better than other methods with root-mean-square error (RMSE) of 3.29 bpm. With respect to the classification of breathing patterns, the established neural network performs better than support vector machine-based classifiers with the accuracy, precision, recall, and F1 of 89.0%, 89.0%, 90.5%, and 89.0%, respectively. The obtained decision-making information and some original information are sent to the user’s smartphone via a cloud service platform. In a way, due to its low-price, noncontact, and portable merits, the established system can be seen as a “respiratory consultant” by your side.

Respiratory pattern is a representation of human breathing activity, which can reflect people's physical and psychological condition. Capturing the unexpected abnormal respiratory pattern unobtrusively of the patient or the potential patient has great significance. In the current work, we attempt to capitalize on depth camera and deep learning architecture to achieve the accurate and unobtrusive measurement of abnormal respiratory patterns, and the whole system can classify multiple people's respiratory patterns in a real-time manner. The challenges in this task are threefold: 1) the real-time online system means that the Region of Interest (ROI) needs to be located and tracked automatically; 2) the amount of real-world data is not enough for training to obtain the robust deep neural network; and 3) the intraclass variation is large and the outer class variation is small. Consequently, human joints tracking is applied to determine the location of subjects shoulder and chest. Based on the characteristics of actual respiratory signals, a novel and efficient respiratory simulation model (RSM) is proposed to generate abundant and high-quality training data. Finally, we apply a gated recurrent unit (GRU) neural network with bidirectional and attentional mechanisms (BI-AT-GRU) to classify six clinically significant respiratory patterns (Eupnea, Tachypnea, Bradypnea, Biots, Cheyne-Stokes, and Central-Apnea). The performance of the obtained BI-AT-GRU is tested by the data that is actually measured by the depth camera. The experimental results demonstrate that the proposed model can classify six different respiratory patterns with the accuracy, precision, recall, and F1 of 94.5%, 94.4%, 95.1%, and 94.8%, respectively. In comparative experiments, the obtained BI-AT-GRU specific to respiratory pattern classification outperforms the existing state-of-the-art, viz., BI-AT-LSTM, GRU, long short-term memory (LSTM), and BI-AT-GRU. Moreover, other experimental results indicate that the proposed online measuring system, deep neural network, and the modeling ideas have the potential to be extended to the large-scale applications, such as public places, sleep scenario, and office environment. The demo videos of the proposed system are available at: https://doi.org/10.6084/m9.figshare.11493666.v1.

The increasing number of mobile devices challenges the current radio frequency (RF) networks, e.g. wireless fidelity (WiFi) networks. Light Fidelity (LiFi) is considered as a promising complementary technology, which operates within the visible light spectrum and infrared spectrum. In an indoor scenario, a hybrid LiFi/WiFi network (HLWN) provides a potential solution to future wireless communications where LiFi augments WiFi in providing ultra-high speed and low latency wireless connectivity. In this paper, dynamic load balancing (LB) with handover in HLWNs is studied. The orientation-based random waypoint (ORWP) mobility model is considered to provide a more realistic framework to evaluate the performance of HLWNs. Based on the low-pass filtering effect of the LiFi channel, we firstly propose an orthogonal frequency division multiplexing access (OFDMA)-based resource allocation (RA) method in LiFi systems. Also, an enhanced evolutionary game theory (EGT)-based LB scheme with handover in HLWNs is proposed. In the EGT scheme, each user adapts their strategy to improve the payoff until LB is achieved across LiFi and WiFi. Then, the LiFi system uses the proposed OFDMA-based RA method while the WiFi system applies the carrier sense multiple access with collision detection (CSMA/CA). Simulation results show that in the LiFi system the OFDMA-based RA scheme outperforms the time division multiple access (TDMA) scheme in terms of both user data rate and fairness. Regarding LB in HLWNs, the proposed EGT scheme can achieve a remarkable enhancement in throughput compared to benchmark schemes, such as hard threshold (HT) scheme and random access point assignment (RAA) scheme.

With the significant increase in wireless data traffic in recent years, the scarce radio frequency (RF) spectrum can no longer guarantee the capacity needed to meet the future growth in mobile traffic demand. New applications such as virtual reality and augmented reality further increase this demand. The emergence of high speed visible light communication (VLC) offers an opportunity to mitigate the looming spectrum crisis. However, the power consumption of a VLC link due to incoherent transmission is a major concern for system designers. Only a few studies have addressed this issue. In this paper, a theoretical study on the relationship between the power consumption and the data rate of a high speed VLC link is presented. The considered VLC link is based on direct-current-biased optical orthogonal frequency division multiplexing (DCO - OFDM) and on-off keying (OOK). The effects of spatial modulation (SM) are also investigated. The presented results show that the optimal operating bandwidth can be determined for a SM DCO-OFDM system to achieve the highest power efficiency possible. The study provides a guideline to configure a VLC system in order to optimize power efficiency for different data rate requirements.

Light fidelity (LiFi), using light emitting devices such as light emitting diodes (LEDs) which are operating in the visible light spectrum between 400 and 800 THz, provides a new layer of wireless connectivity within existing heterogeneous radio frequency wireless networks. Link data rates of 10 Gbps from a single transmitter have been demonstrated under ideal laboratory conditions. Synchronization is one of these issues usually assumed to be ideal. However, in a practical deployment, this is no longer a valid assumption. Therefore, we propose for the first time a low-complexity maximum likelihood-based timing synchronization process that includes frame detection and sampling clock synchronization for direct current-biased optical orthogonal frequency division multiplexing LiFi systems. The proposed timing synchronization structure can reduce the high-complexity two-dimensional search to two low-complexity one-dimensional searches for frame detection and sampling clock synchronization. By employing a single training block, frame detection can be realized, and then sampling clock offset (SCO) and channels can be estimated jointly. We propose three frame detection approaches, which are robust against the combined effects of both SCO and the low-pass characteristic of LEDs. Furthermore, we derive the Cramér–Rao lower bounds (CRBs) of SCO and channel estimations, respectively. In order to minimize the CRBs and improve synchronization performance, a single training block is designed based on the optimization of training sequences, the selection of training length, and the selection of direct current (DC) bias. Therefore, the designed training block allows us to analyze the trade-offs between estimation accuracy, spectral efficiency, energy efficiency, and complexity. The proposed timing synchronization mechanism demonstrates low complexity and robustness benefits and provides performance significantly better than achieved with existing methods.

Light Fidelity (LiFi) is a recently proposed technology that combines illumination and high speed wireless communication using light emitting diodes (LEDs). Unlike radio frequency (RF) channels, LiFi channels do not exhibit fading characteristics as the detector size is much larger than the wavelength. Another distinguishing feature is that LiFi channels are mainly affected by the low-pass filtering effect caused by LEDs, while the multipath effect is inconspicuous. Therefore, unlike in RF systems, LiFi systems can hardly achieve the conventional multi-user diversity gain when using orthogonal frequency division multiplexing access (OFDMA). Due to the LED characteristics, users with high direct current (DC) signal-to-noise ratio (SNR) may be able to use a large modulation bandwidth in LiFi systems. This means that users with good channel conditions can be more likely to utilise high-frequency resources. In this paper, resource allocation (RA) in OFDMAbased LiFi systems is investigated and an optimal RA scheme and a low- complexity RA scheme are proposed. Simulation results show that by efficiently using high- frequency bandwidth resources, the RA schemes in OFDMA systems outperform those in TDMA systems in terms of both data rate and user fairness. Also, the low-complexity RA scheme is able to achieve nearoptimal performance at a reduction of 90% in computational complexity.

Light fidelity (LiFi) uses light emitting diodes (LEDs) for high-speed wireless communications. Since an LED lamp covers a small area, a LiFi system with multiple access points (APs) can offer a significantly high spatial throughput. However, the spatial distribution of data rates achieved by LiFi fluctuates because users experience inter-cell interference from neighboring LiFi APs. In order to guarantee a quality of service (QoS) for all users in the network, an RF network is considered as an additional wireless networking layer. This hybrid LiFi/RF network enables users with low levels of optical signals to achieve the desired QoS by migrating to the RF network. With regard to moving users, the hybrid LiFi/RF system dynamically allocates either a LiFi AP or an RF AP to users based on their channel state information. In this paper, a dynamic load balancing scheme is proposed, which considers the handover overhead in order to improve the overall system throughput. Joint optimization algorithm (JOA) and separate optimization algorithm (SOA), which jointly and separately optimize the AP assignment and resource allocation, respectively, are proposed. Simulation results show that SOA can offer a better performance/complexity tradeoff than JOA for system load balancing.

Light Fidelity (LiFi) is a recently proposed technology that uses 300 THz visible light spectrum for high speed wireless communications as well as providing illumination. Basically, a LiFi access point (AP) covers only a few square meters, enabling a dense deployment of LiFi APs to improve the network throughput. However, channel blockage and shadowing in conjunction with inter-cell interference compromise the connectivity and system throughput of LiFi networks. In this paper, a network structure that combines LiFi with the conventional radio frequency (RF) system is considered. Users experiencing strong blockages can be switched to the RF system to achieve a higher data rate. In this paper, blockages, random orientation of LiFi receivers, and the user data rate requirement are characterised to model a practical communication scenario. A novel load balancing (LB) scheme based on evolutionary game theory is proposed for hybrid LiFi/RF networks. The performance of the proposed scheme is comprehensively analyzed. Results show that compared to state-of-the-art LB algorithms, the proposed scheme greatly improves user satisfaction levels at reduced computational complexity. Also, an optimal orientation of LiFi receivers and blockage density in hybrid networks would maximize the users quality of service.

Light Fidelity (LiFi) is a recently proposed technology that combines illumination and high speed wireless communication using light emitting diodes (LEDs). Since the used electromagnetic spectrum does not overlap with the radio frequency (RF) spectrum, a small cell LiFi attocell network can be added to the conventional RF network as an additional networking layer in order to mitigate the data traffic bottlenecks in high density environments. In such a hybrid LiFi/RF network where the LiFi attocell covers a few square meters, user movement may prompt frequent handovers, and the handover overhead would degrade the system throughput. The goal is to reduce the handover overhead by appropriately assigning users to either the RF or the LiFi access point (AP). In this study, a fuzzy logic (FL) based dynamic handover scheme is proposed. This FL scheme uses not only the channel state information (CSI), but also the user speed and desired data rate to determine whether a handover needs to be prompted. Simulation shows that the proposed scheme outperforms the conventional handover algorithms, and the performance improvement is approximately 40% in terms of both data rate and user satisfaction level.

Light Fidelity (LiFi) uses light emitting diodes (LEDs) for high speed wireless communications. Since employing a different range of the electromagnetic spectrum from radio frequency (RF) communications, LiFi can significantly alleviate the traffic bottlenecks in high density RF scenarios, typically present in an indoor environment. Hence, a combination of LiFi and RF networks becomes a promising candidate for future indoor wireless communications. In a practical indoor scenario, the optical interference from neighbouring LiFi access points (APs) and the blockages of line-of-sight (LoS) optical channels induced by people and objects are the main factors that cause significant optical channel variations. In this study, the effect of these two factors on the system throughput of a hybrid LiFi/RF network is investigated. In order to offer a fair comparison, area data rate, which is defined as the system throughput in a unit area, is used for performance evaluation. The simulation shows that there is an optimal distance between two neighbouring LiFi APs to achieve the highest area data rate. In addition, the area data rate increases with the density of blockages when the blockage density is below a certain threshold.

The Internet of Things (IoT) is a new generation of network that can remotely and intelligently control distributed objects. Due to the large number of objects in the IoT, a high data traffic for the object communications is required, which is mostly routed through wireless links. However, the available spectrum for radio frequency (RF) wireless communications is exhausted so that each user in the IoT can only achieve very low data rate. In order to offer a better service to users, a light fidelity (Li-Fi) and radio frequency (RF) hybrid network is considered, where Li-Fi uses the large spectrum of visible light to achieve a high data rate, and the RF system guarantees a seamless coverage. In this study, a load balancing (LB) algorithm for the Li-Fi/RF hybrid IoT network is proposed based on evolutionary game theory (EGT). A key feature of the proposed algorithm is that users autonomously select the APs and adapt their strategies. Thus, compared with the conventional centralised algorithm, the computation load of the central unit (CU) can be reduced by using the EGT algorithm. Moreover, simulation results show that the proposed algorithm outperforms the conventional centralised algorithms in terms of the user satisfaction.

In this paper, a hybrid network combining visible light communication (VLC) with a radio frequency (RF) wireless local area network (WLAN) is considered. In indoor scenarios, a light fidelity (Li-Fi) access point (AP) can provide very high throughput and satisfy any illumination demands while wireless fidelity (Wi-Fi) offers basic coverage. Such a hybrid network with both fixed and mobile users has the problem of variable user locations, and thus large fluctuations in spatially distributed traffic demand. Generally, a handover occurs in such a method when a user is allocated by the central controller unit to a different AP which is better placed to serve the user. In order to be representative of real deployments, this paper studies the problem of load balancing of a dynamic system where we consider the signalling overhead for handover. We propose a scheme for dynamic allocation of resources to users, where the utility function takes into account both throughput and fairness. The simulation results show that there is a trade off between the aggregate throughput and user fairness when handover overhead is considered. The proposed dynamic scheme always outperforms the considered benchmarks in terms of fairness and can achieve better aggregate throughput in the case of low user density.

In heterogeneous cellular networks, cross-tier inter-cell interference is often in mixed interference scenario where the macro-cell causes strong interference to pico-cells while pico-cells only cause weak interference to the macro-cell. In this scenario, the popular interference coordination schemes using power control or time/frequency division multiplexing are far from achieving the spectrum efficiency potential. Exploiting the difference of transmit powers and channel gains in heterogeneous networks, the transmission schemes based on interference cancelation have great opportunity to gain more throughput benefit. In this paper, we propose a coordinated precoding and proactive interference cancelation scheme, where the precoding design is based on the known decoding order and is to maximize the sum-rate of two interfering users. Since the optimization problem is non-convex, we find a local maximum by constructing a concave lower bound of the objective function and iteratively tightening it. Simulation results show that the network throughput is remarkably improved in mixed interference scenarios relative to orthogonal division scheme and coordinated multipoint transmission scheme with zero forcing precoding.

With the increasing number of mobile terminals, the capacity of cellular network can hardly satisfy the user requirement in the future. In next generation cellular systems, heterogeneous network is proposed to improve the spatial spectrum efficiency. In this paper, we study a joint coding scheme to increase the achievable sum-rate of multi-carrier heterogeneous systems, where we introduce transmission cooperation among subcarriers in the amplitude space to assist interference elimination at the receiver. Specifically, we propose to transmit information through cross links on some of the subcarriers where the users suffer from the strong interference, and use this information at the receiver to cancel the interference experienced on other subcarriers. We develop the direct-link transmission strategy using layered lattice code, and design subcarrier allocation algorithm between direct-link and cross-link transmissions. Simulation results show that the proposed joint coding scheme achieves higher sum rate than separated coding schemes in strong interference channels.