Joint Clustering and Resource Allocation Optimization in Ultra-Dense Networks with Multiple Drones as Small Cells Using Game Theory.

In this study, we consider the combination of clustering and resource allocation based on game theory in ultra-dense networks that consist of multiple macrocells using massive multiple-input multiple-output and a vast number of randomly distributed drones serving as small-cell base stations. In particular, to mitigate the intercell interference, we propose a coalition game for clustering small cells, with the utility function being the ratio of signal to interference. Then, the optimization problem of resource allocation is divided into two subproblems: subchannel allocation and power allocation. We use the Hungarian method, which is efficient for solving binary optimization problems, to assign the subchannels to users in each cluster of small cells. Additionally, a centralized algorithm with low computational complexity and a distributed algorithm based on the Stackelberg game are provided to maximize the network energy efficiency (EE). The numerical results demonstrate that the game-based method outperforms the centralized method in terms of execution time in small cells and is better than traditional clustering in terms of EE.

AI-Driven Aeronautical Ad Hoc Networks for 6G Wireless: Challenges, Opportunities, and the Road Ahead.

Aeronautical ad hoc network (AANET) has been considered a promising candidate to complete the vision of "Internet in the sky" by supporting high-speed broadband connections on airplanes for 6G networks. However, the specific characteristics of AANET restrict the applicability of conventional topology and routing management algorithms. Here, these conventional methodologies reduce the packet delivery success of AANET with higher transfer delay. At that point, the artificial intelligence (AI)-driven solutions have been adapted to AANET to provide intelligent frameworks and architectures to cope with the high complexity. The AI-driven AANET can provide intelligent topology formation, sustainability, and routing management decisions in an automated fashion by considering its specific characteristics during the learning operations. More clearly, AI-driven AANETs support intelligent management architectures, overcoming conventional methodologies' drawbacks. Although AI-based management approaches are widely used in terrestrial networks, there is a lack of a comprehensive study that supports AI-driven solutions for AANETs. To this end, this article explores the possible utilization of primary AI methodologies on the road to AI-driven AANET. Specifically, the article addresses unsupervised, supervised, and reinforcement learning as primary AI methodologies to enable intelligent AANET topology formation, sustainability, and routing management. Here, we identify the challenges and opportunities of these primary AI methodologies during the execution of AANET management. Furthermore, we discuss the critical issue of security in AANET before providing open issues.

Multiclass Classification of Metrologically Resourceful Tripartite Quantum States with Deep Neural Networks.

Quantum entanglement is a unique phenomenon of quantum mechanics, which has no classical counterpart and gives quantum systems their advantage in computing, communication, sensing, and metrology. In quantum sensing and metrology, utilizing an entangled probe state enhances the achievable precision more than its classical counterpart. Noise in the probe state preparation step can cause the system to output unentangled states, which might not be resourceful. Hence, an effective method for the detection and classification of tripartite entanglement is required at that step. However, current mathematical methods cannot robustly classify multiclass entanglement in tripartite quantum systems, especially in the case of mixed states. In this paper, we explore the utility of artificial neural networks for classifying the entanglement of tripartite quantum states into fully separable, biseparable, and fully entangled states. We employed Bell's inequality for the dataset of tripartite quantum states and train the deep neural network for multiclass classification. This entanglement classification method is computationally efficient due to using a small number of measurements. At the same time, it also maintains generalization by covering a large Hilbert space of tripartite quantum states.

Development of a Spatial Decision Support System for Real-Time Flood Early Warning in the Vu Gia-Thu Bon River Basin, Quang Nam Province, Vietnam.

Vu Gia-Thu Bon (VGTB) river basin is an area where flash flood and heavy flood events occur frequently, negatively impacting the local community and socio-economic development of Quang Nam Province. In recent years, structural and non-structural solutions have been implemented to mitigate damages due to floods. However, under the impact of climate change, natural disasters continue to happen unpredictably day by day. It is, therefore, necessary to develop a spatial decision support system for real-time flood warnings in the VGTB river basin, which will support in ensuring the area's socio-economic development. The main purpose of this study is to develop an online flood warning system in real-time based on Internet-of-Things (IoT) technologies, GIS, telecommunications, and modeling (Soil and Water Assessment Tool (SWAT) and Hydrologic Engineering Center's River Analysis System (HEC-RAS)) in order to support the local community in the vulnerable downstream areas in the event of heavy rainfall upstream. The structure of the designed system consists of these following components: (1) real-time hydro-meteorological monitoring network, (2) IoT communication infrastructure (Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), wireless networks), (3) database management system (bio-physical, socio-economic, hydro-meteorological, and inundation), (4) simulating and predicting model (SWAT, HEC-RAS), (5) automated simulating and predicting module, (6) flood warning module via short message service (SMS), (7) WebGIS, application for providing and managing hydro-meteorological and inundation data, and (8) users (citizens and government officers). The entire operating processes of the flood warning system (i.e., hydro-meteorological data collecting, transferring, updating, processing, running SWAT and HEC-RAS, visualizing) are automated. A complete flood warning system for the VGTB river basin has been developed as an outcome of this study, which enables the prediction of flood events 5 h in advance and with high accuracy of 80%.

PS-CARA: Context-Aware Resource Allocation Scheme for Mobile Public Safety Networks.

The fifth-generation (5G) communications systems are expecting to support users with diverse quality-of-service (QoS) requirements. Beside these requirements, the task with utmost importance is to support the emergency communication services during natural or man-made disasters. Most of the conventional base stations are not properly functional during a disaster situation, so deployment of emergency base stations such as mobile personal cell (mPC) is crucial. An mPC having moving capability can move in the disaster area to provide emergency communication services. However, mPC deployment causes severe co-channel interference to the users in its vicinity. The problem in the existing resource allocation schemes is its support for static environment, that does not fit well for mPC. So, a resource allocation scheme for mPC users is desired that can dynamically allocate resources based on users’ location and its connection establishment priority. In this paper, we propose a public safety users priority-based context-aware resource allocation (PS-CARA) scheme for users sum-rate maximization in disaster environment. Simulations results demonstrate that the proposed PS-CARA scheme can increase the user average and edge rate around 10.3% and 32.8% , respectively because of context information availability and by prioritizing the public safety users. The simulation results ensure that call blocking probability is also reduced considerably under the PS-CARA scheme.

Entanglement detection with artificial neural networks.

Quantum entanglement is one of the essential resources involved in quantum information processing tasks. However, its detection for usage remains a challenge. The Bell-type inequality for relative entropy of coherence serves as an entanglement witness for pure entangled states. However, it does not perform reliably for mixed entangled states. This paper constructs a classifier by employing the relationship between coherence and entanglement for supervised machine learning methods. This method encodes multiple Bell-type inequalities for the relative entropy of coherence into an artificial neural network to detect the entangled and separable states in a quantum dataset.

TwinPort: 5G drone-assisted data collection with digital twin for smart seaports.

Numerous ports worldwide are adopting automation to boost productivity and modernize their operations. At this point, smart ports become a more important paradigm for handling increasing cargo volumes and increasing operational efficiency. In fact, as ports become more congested and cargo volumes increase, the need for accurate navigation through seaports is more pronounced to avoid collisions and the resulting consequences. To this end, digital twin (DT) technology in the fifth-generation (5G) networks and drone-assisted data collection can be combined to provide precise ship maneuvering. In this paper, we propose a DT model using drone-assisted data collection architecture, called TwinPort, to offer a comprehensive port management system for smart seaports. We also present a recommendation engine to ensure accurate ship navigation within a smart port during the docking process. The experimental results reveal that our solution improves the trajectory performance by approaching the desired shortest path. Moreover, our solution supports significantly reducing financial costs and protecting the environment by reducing fuel consumption.

A Wearable-based Preventive Model To Promote Oral Health Through Personalized Notification.

Wearable technology has great potential to develop human-centric healthcare applications. It reshapes our lifestyle by providing information related to physical activities, sleep monitoring, or heartbeat rhythms. In this paper, we present an innovative model for oral healthcare, which is prevention-focused to notify individuals about cleaning teeth activity. It is based on a wrist-worn accelerometer device and has two components-first, a computationally lightweight feature extractor-secondly, a robust feed-forward neural network to recognize the cleaning teeth activity. The model performance is measured using standard performance metric F1 - score (i.e., 98%), which shows the applicability in a real-life scenario. The trained model can reside inside the smartwatch as a wrist-worn wearable. It would generate personalized notifications if s/he skipped the toothbrush activity. Furthermore, it notifies the users to change the toothbrush after three months, reducing the cognitive burden. Clinical Relevance-This work help the individuals to maintain their oral health using smartwatches as a wearable device.

Deep learning models for forecasting dengue fever based on climate data in Vietnam.

BACKGROUND: Dengue fever (DF) represents a significant health burden in Vietnam, which is forecast to worsen under climate change. The development of an early-warning system for DF has been selected as a prioritised health adaptation measure to climate change in Vietnam. OBJECTIVE: This study aimed to develop an accurate DF prediction model in Vietnam using a wide range of meteorological factors as inputs to inform public health responses for outbreak prevention in the context of future climate change. METHODS: Convolutional neural network (CNN), Transformer, long short-term memory (LSTM), and attention-enhanced LSTM (LSTM-ATT) models were compared with traditional machine learning models on weather-based DF forecasting. Models were developed using lagged DF incidence and meteorological variables (measures of temperature, humidity, rainfall, evaporation, and sunshine hours) as inputs for 20 provinces throughout Vietnam. Data from 1997-2013 were used to train models, which were then evaluated using data from 2014-2016 by Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). RESULTS AND DISCUSSION: LSTM-ATT displayed the highest performance, scoring average places of 1.60 for RMSE-based ranking and 1.95 for MAE-based ranking. Notably, it was able to forecast DF incidence better than LSTM in 13 or 14 out of 20 provinces for MAE or RMSE, respectively. Moreover, LSTM-ATT was able to accurately predict DF incidence and outbreak months up to 3 months ahead, though performance dropped slightly compared to short-term forecasts. To the best of our knowledge, this is the first time deep learning methods have been employed for the prediction of both long- and short-term DF incidence and outbreaks in Vietnam using unique, rich meteorological features. CONCLUSION: This study demonstrates the usefulness of deep learning models for meteorological factor-based DF forecasting. LSTM-ATT should be further explored for mitigation strategies against DF and other climate-sensitive diseases in the coming years.

Risk-Aware Identification of Highly Suspected COVID-19 Cases in Social IoT: A Joint Graph Theory and Reinforcement Learning Approach.

The recent outbreak of the coronavirus disease 2019 (COVID-19) has rapidly become a pandemic, which calls for prompt action in identifying suspected cases at an early stage through risk prediction. To suppress its further spread, we exploit the social relationships between mobile devices in the Social Internet of Things (SIoT) to help control its propagation by allocating the limited protective resources to the influential so-called high-degree individuals to stem the tide of precipitated spreading. By exploiting the so-called differential contact intensity and the infectious rate in susceptible-exposed-infected-removed (SEIR) epidemic model, the resultant optimization problem can be transformed into the minimum weight vertex cover (MWVC) problem of graph theory. To solve this problem in a high-dynamic random network topology, we propose an adaptive scheme by relying on the graph embedding technique during the state representation and reinforcement learning in the training phase. By relying on a pair of real-life datasets, the results demonstrate that our scheme can beneficially reduce the epidemiological reproduction rate of the infection. This technique has the potential of assisting in the early identification of COVID-19 cases.

Strategies for Coexistence in Molecular Communication.

Some of the most ambitious applications of molecular communications are expected to lie in nanomedicine and advanced manufacturing. In these domains, the molecular communication system is surrounded by a range of biochemical processes, some of which may be sensitive to chemical species used for communication. Under these conditions, the biological system and the molecular communication system impact each other. As such, the problem of coexistence arises, where both the reliability of the molecular communication system and the function of the biological system must be ensured. In this paper, we study this problem with a focus on interactions with biological systems equipped with chemosensing mechanisms, which arises in a large class of biological systems. We motivate the problem by considering chemosensing mechanisms arising in bacteria chemotaxis, a ubiquitous and well-understood class of biological systems. We, then, propose strategies for a molecular communication system to minimize the disruption of biological system equipped with a chemosensing mechanism. This is achieved by exploiting tools from the theory of chemical reaction networks. To investigate the capabilities of our strategies, we obtain fundamental information theoretic limits by establishing a new connection with the problem of covert communications.