Mission-critical Applications Research Articles

Channel Estimation for Reconfigurable Intelligent Surface Assisted High-Mobility Wireless Systems

Next-generation communication systems aim for providing pervasive services, including the high-mobility scenarios routinely encountered in mission-critical applications. Hence we harness the recently-developed reconfigurable intelligent surfaces (RIS) to assist the high-mobility cell-edge users. However, in the face of high Doppler frequencies, the existing RIS channel estimation techniques that assume block fading generally result in irreducible error floors. In order to mitigate this problem, we propose a new RIS channel estimation technique, which is the first one that performs minimum mean square error (MMSE) based interpolation for the sake of taking into account the time-varying nature of fading even within the coherence time. The RIS modelling invokes only passive elements without relying on RF chains, where both the direct link and RIS-reflected links as well as both the line-of-sight (LoS) and non-LoS (NLoS) paths are taken into account. As a result, the cascaded base station (BS)-RIS-user links involve the multiplicative concatenation of the channel coefficients in the LoS and NLoS paths across the two segments of the BS-RIS and RIS-user links. Against this background, we model the multiplicative RIS fading correlation functions for the first time in the literature, which facilitates MMSE interpolation for estimating the high-dimensional and high-Doppler RIS-reflected fading channels. Our simulation results demonstrate that for a vehicle travelling at a speed as high as 90 mph, employing a low-complexity RIS at the cell-edge using as few as 16 RIS elements is sufficient for achieving substantial power-effieincy gains, where the Doppler-induced error floor is mitigated by the proposed channel estimation technique.

Enhanced Human–Robot Interface With Operator Physiological Parameters Monitoring and 3D Mixed Reality

Remote robotic interventions and maintenance tasks are frequently required in hazardous environments. Particularly, missions with a redundant mobile manipulator in the world’s most complex machine, the CERN Large Hadron Collider, are performed in a sensitive underground environment with radioactive or electromagnetic hazards, bringing further challenges in safety and reliability. The mission’s success depends on the robot’s hardware and software, and when the tasks become too unpredictable to execute autonomously, the operators need to make critical decisions. However, in most current human-machine systems, the state of the human is neglected. In this context, a novel 3D Mixed Reality (MR) human-robot interface with the Operator Monitoring System (OMS) was developed to advance safety and task efficiency with improved spatial awareness, advanced manipulator control, and collision avoidance. However, new techniques could increase the system’s sophistication and add to the operator’s workload and stress. Therefore, for operational validation, the 3D MR interface had to be compared with an operational 2D interface, which has been used in hundreds of interventions. With the 3D MR interface, the execution of precise approach tasks was faster, with no increased workload or physiological response. The new 3D MR techniques improved the teleoperation quality and safety while maintaining similar effects on the operator. The OMS worked jointly with the interface and performed well with operators with varied teleoperation backgrounds facing a stressful real telerobotic scenario in the LHC. The paper contributes to the methodology for human-centred interface evaluation incorporating the user’s physiological state: heart rate, respiration rate and skin electrodermal activity, and combines it with the NASA TLX assessment method, questionnaires, and task execution time. It provides novel approaches to operator state identification, the GUI-OMS software architecture, and the evaluation of the 3D MR techniques. The solutions can be practically applied in mission-critical applications, such as telesurgery, space robotics, uncrewed transport vehicles and semi-autonomous machinery.

Enabling All In-Edge Deep Learning: A Literature Review

In recent years, deep learning (DL) models have demonstrated remarkable achievements on non-trivial tasks such as speech recognition, image processing, and natural language understanding. One of the significant contributors to the success of DL is the proliferation of end devices that act as a catalyst to provide data for data-hungry DL models. However, computing DL training and inference still remains the biggest challenge. Moreover, most of the time central cloud servers are used for such computation, thus opening up other significant challenges, such as high latency, increased communication costs, and privacy concerns. To mitigate these drawbacks, considerable efforts have been made to push the processing of DL models to edge servers (a mesh of computing devices near end devices). Recently, the confluence point of DL and edge has given rise to edge intelligence (EI), defined by the International Electrotechnical Commission (IEC) as the concept where the data is acquired, stored, and processed utilizing edge computing with DL and advanced networking capabilities. Broadly, EI has six levels of categories based on the three locations where the training and inference of DL take place, e.g., cloud server, edge server, and end devices. This survey paper focuses primarily on the fifth level of EI, called all in-edge level, where DL training and inference (deployment) are performed solely by edge servers. All in-edge is suitable when the end devices have low computing resources, e.g., Internet-of-Things, and other requirements such as latency and communication cost are important such as in mission-critical applications (e.g., health care). Besides, 5G/6G networks are envisioned to use all in-edge. Firstly, this paper presents all in-edge computing architectures, including centralized, decentralized, and distributed. Secondly, this paper presents enabling technologies, such as model parallelism, data parallelism, and split learning, which facilitates DL training and deployment at edge servers. Thirdly, model adaptation techniques based on model compression and conditional computation are described because the standard cloud-based DL deployment cannot be directly applied to all in-edge due to its limited computational resources. Fourthly, this paper discusses eleven key performance metrics to evaluate the performance of DL at all in-edge efficiently. Finally, several open research challenges in the area of all in-edge are presented.

Application of nature inspired optimization algorithm on hierarchal LEACH protocol for improved performance

In today’s scenario Wireless Sensor Network is playing a dynamic role with the advancement in IOT for mission critical applications due to the fact that these applications are either event driven or time driven applications. Sensor network comprises of battery operated tiny sensors for sensing any change in the environment since the battery life is limited so is the sensor life. One solution to overcome this problem is the use of clustering protocol. A lot of optimization techniques are employed for performance improvement of the hierarchal LEACH routing protocol. This paper explores the three types of Foraging behavior for cluster head selection which means the process to search for food or the energy of the node so that it can be elected as CH. A fitness function is defined relating to residual energy, CH distance to Base station, position of base station. Theses algorithm progresses on the basis of the energy of sensor node in the deployed network. Here the higher energy of node is analogous to food for which the search goes on; in doing so the best CH is selected. The algorithm uses the best location of the node. The overall performance of the network is improved in terms of Energy consumption; packet delivery ratio metrics the results are compared with the existing LEACH protocol.

Discover and safe: an automated security management system for educational institutions

In this paper, we proposed discover and safe (DaS) automatic security system by the help of face recognition. The focus of this automated system is to provide high-level security to manage the entry of people with face detection. This paper proposes haar cascade algorithm with dip libraries to create a camera-based real-time security management system through face detection and recognition. Haar cascade algorithm is an object detection algorithm which is mainly used in identifying face of any image or a real-time video (by webcam or building camera). The DaS framework worked on two phases: 1) to locate whether the VM is an unintended security; 2) to secure mission critical applications. The DaS access system implemented the face encoding scheme to detect the face and eye which works effectively on light and illumination changes. The results show that DaS framework can Armor the VM from obscured security problems and steal hidden doors against the attackers.

Swift HARQ Based on Machine Learning for Latency Minimization in URLLC

Ultra-reliable low-latency communication (URLLC) has been introduced in the 5th Generation (5G) radios for mission-critical applications that demand strict reliability and latency traffic to guarantee the rapid delivery of short packets (up to 1 ms) with a success probability rate of 99.999%. The challenging reliability and latency requirements of URLLC have significant impact on the air-interface design, especially on the Hybrid Automatic Repeat reQuest (HARQ) mechanism. This study focuses on satisfying link latency requirements by reducing the delay that arises in the presence of the HARQ operation. To this end, we propose a Swift HARQ protocol empowered by machine learning techniques to estimate the decodability of a packet early enough within its maximum number of allowable retransmission attempts. This can allow the transmitter to react faster by dropping the non-decodable packets, or activating the repetition mode where parts of the HARQ feedback can be omitted. As shown through system-level simulations, the proposed model achieves a delay reduction of more than 50% compared to the traditional HARQ, and increases the system throughput by up to 40% when multiple HARQ retransmissions are required.

MEET: Mobility-Enhanced Edge inTelligence for Smart and Green 6G Networks

Edge intelligence is an emerging paradigm for real-time training and inference at the wireless edge, thus enabling mission-critical applications. Accordingly, base stations (BSs) and edge servers (ESs) need to be densely deployed, leading to huge deployment and operation costs, in particular energy costs. In this article, we propose a new framework called Mobility-Enhanced Edge inTelligence (MEET), which exploits the sensing, communication, computing, and self-powering capabilities of intelligent connected vehicles for smart and green 6G networks. Specifically, the operators can incorporate infrastructural vehicles as movable BSs or ESs, and schedule them in a more flexible way to align with communication and computation traffic fluctuations. Meanwhile, the remaining compute resources of opportunistic vehicles are exploited for edge training and inference, where mobility can further enhance edge intelligence by bringing more compute resources, communication opportunities, and diverse data. In this way, the deployment and operation costs are spread over the vastly available vehicles so that edge intelligence is realized cost-effectively and sustainably. Furthermore, these vehicles can be either powered by renewable energy to reduce carbon emissions or charged more flexibly during off-peak hours to cut electricity bills.

Dynamic Distributed Monitoring for 6LoWPAN-based IoT Networks

Mission-criticalal Internet of Things (IoT)-based networks are increasingly employed in daily and industrial infrastructures. The resilience of such networks is crucial. Given IoT networks’ constantly changing nature, it is necessary to provide dependability and sustainability. A robust network monitoring can reinforce reliability, such that the monitoring mechanism adapts itself to real-time network instabilities. This work proposes a proactive, dynamic, and distributed network monitoring mechanism with monitor placement and scheduling for 6LoWPAN-based IoT networks intended for mission-critical applications. The proposed mechanism aims to ensure real-time monitoring coverage while respecting the limited and changing power resources of devices to prolong the network lifetime.

Wide-Speed Range Sensorless Control of Five-Phase PMSM Drive under Healthy and Open Phase Fault Conditions for Aerospace Applications

This paper presents a speed sensorless control of a five-phase PMSM in healthy operation and under the Open-Phase Fault on any phase of the machine. The solution is recommended for mission-critical applications requiring high reliability capacities, such as Aerospace applications. An adapted Active Fault Tolerant Control is proposed with the aim of obtaining electromechanical torque as close as possible to that normally developed by a machine working in healthy condition. In instances of a loss of power to one phase of the machine, a reconfiguration of the control law is performed to ensure the continuity of service and to maintain acceptable control performances without requiring a hardware rearrangement of the power architecture. The motor rotation speed and position, required for the Field Oriented Control (FOC) of the stator currents, are estimated using a Back-Electromotive Forces (Back-EMF) observer based on a mathematical model of the motor and implemented in the stator diphase reference frame. Different electrical models that describe the behavior of the five-phase machine in the normal and degraded operations are given. Experimental results on a 1.25 kW synchronous PM machine are shown to confirm the effectiveness of the motor control.

Improved Quality of Services with Intelligent MAC in Wireless Sensor Networks for Mission Critical Applications

Wireless sensor networks are very feasible to monitor where human reach is impossible. But conserving the limited resource and maintaining Quality of service is the challenging task. There is most need to design an algorithm to maintain quality of services. In this paper we have designed node layered division MAC with adaptive listening based on the queue size at the transmitting cluster node. The proposed protocol attenuates the problem of collision and unfair distribution of power among the nodes. When compared with the existing algorithms, IQMAC outperforms in terms of network lifetime, delay, PDR and collision probability.

Backdoor Attacks on Deep Neural Networks via Transfer Learning from Natural Images

Backdoor attacks are a serious security threat to open-source and outsourced development of computational systems based on deep neural networks (DNNs). In particular, the transferability of backdoors is remarkable; that is, they can remain effective after transfer learning is performed. Given that transfer learning from natural images is widely used in real-world applications, the question of whether backdoors can be transferred from neural models pretrained on natural images involves considerable security implications. However, this topic has not been evaluated rigorously in prior studies. Hence, in this study, we configured backdoors in 10 representative DNN models pretrained on a natural image dataset, and then fine-tuned the backdoored models via transfer learning for four real-world applications, including pneumonia classification from chest X-ray images, emergency response monitoring from aerial images, facial recognition, and age classification from images of faces. Our experimental results show that the backdoors generally remained effective after transfer learning from natural images, except for small DNN models. Moreover, the backdoors were difficult to detect using a common method. Our findings indicate that backdoor attacks can exhibit remarkable transferability in more realistic transfer learning processes, and highlight the need for the development of more advanced security countermeasures in developing systems using DNN models for sensitive or mission-critical applications.

XURLLC in 6G with meshed RAN

5G Ultra-Reliable Low Latency Communications Technology (URLLC) will not be able to provide extremely reliable low latency services to the complex networks in 6G. Moreover, URLLC that began with 5G has to be refined and improved in 6G to provide xURLCC (extreme URLCC) with sub-millisecond latency, for supporting diverse mission-critical applications. This paper aims to highlight the importance of peer-to-peer mesh connectivity for services that require xURLLC. Deploying mesh connectivity among RAN nodes would add significant value to the current 5G New Radio (5G NR) enabling 6G to increase flexibility and reliability of the networks while reducing the inherent latency introduced by the core network. To provide a mesh connectivity in RAN, the nodes should be able to communicate with each other directly and be independent from the mobile core network so that data can be directly exchanged between base stations (gNBs) whereas certain aspects of signalling procedure including data session establishment will be managed by RAN itself. In this paper, we introduce several architectural choices for a mesh network topology that could potentially be crucial to a number of applications. In addition, three possible options to create mesh connectivity in RAN are provided, and their pros and cons are discussed in detail.

Federated Learning for IoUT: Concepts, Applications, Challenges and Future Directions

Internet of Underwater Things (IoUT) have gained rapid momentum over the past decade with applications spanning from environmental monitoring and exploration, defence applications, etc. The traditional IoUT systems use machine learning (ML) approaches which cater the needs of reliability, efficiency and timeliness. However, an extensive review of the various studies conducted highlight the significance of data privacy and security in IoUT frameworks as a predominant factor in achieving desired outcomes in mission critical applications. Federated learning (FL) is a secured, decentralized framework which is a recent development in ML, that can help in fulfilling the challenges faced by conventional ML approaches in IoUT. This article presents an overview of the various applications of FL in IoUT, its challenges, open issues and indicates direction of future research prospects.

Adaptive AF/DF Two-Way Relaying in FD Multiuser URLLC System With User Mobility

We consider a full-duplex (FD)-enabled multi-user two-way communication system with adaptive amplify-and-forward (AF)/decode-and-forward (DF) relaying protocol. All the users are assumed to be mobile and to have FD abilities. The effect of mobility, which results in time-selective fading, is modeled using a first-order autoregressive (AR1) process. The fading channel-based approach characterizes the residual self-interference (RSI) at the FD relay, user nodes and is modeled as a Rician distributed random variable. This paper constitutes the most critical use case of 5G, i.e., ultra-reliable low latency communication (URLLC), which adopts short-packets finite blocklength (FB) codes to spin out into the mission-critical applications where strict latency and reliability requirements are highly desirable. The outage performance of the system is studied over independent and non-identically distributed complex Gaussian (Rayleigh envelope) channels with imperfect channel state information (CSI) for with and without URLLC use cases. The closed-form expressions for the outage probability and block error rate (BLER) are derived for the absolute channel power-based scheduling scheme considering the different Doppler power spectra models and the effect of co-channel interference (CCI). The expressions for the asymptotic outage probability are also derived. The presented analysis is compared with baseline schemes, e.g., the results derived with adaptive AF/DF relaying are also compared with both AF and DF relaying, and the performance of the FD transmissions is compared to that of half-duplex (HD) transmissions. The impact of node mobility, RSI, FBL, number of user pairs, and imperfect CSI on the system performance is investigated. Moreover, essential insights are obtained related to the performance gain and region of the superiority of the adaptive AF/DF relaying scheme. The derived analytic results are validated through Monte Carlo simulations. Furthermore, at high transmit power, the outage performance for the adaptive AF/DF protocol approaches the derived asymptotic floor.

DINI: data imputation using neural inversion for edge applications

The edge computing paradigm has recently drawn significant attention from industry and academia. Due to the advantages in quality-of-service metrics, namely, latency, bandwidth, energy efficiency, privacy, and security, deploying artificial intelligence (AI) models at the network edge has attracted widespread interest. Edge-AI has seen applications in diverse domains that involve large amounts of data. However, poor dataset quality plagues this compute regime owing to numerous data corruption sources, including missing data. As such systems are increasingly being deployed in mission-critical applications, mitigating the effects of corrupted data becomes important. In this work, we propose a strategy based on data imputation using neural inversion, DINI. It trains a surrogate model and runs data imputation in an interleaved fashion. Unlike previous works, DINI is a model-agnostic framework applicable to diverse deep learning architectures. DINI outperforms state-of-the-art methods by at least 10.7% in average imputation error. Applying DINI to mission-critical applications can increase prediction accuracy to up to 99% (F1 score of 0.99), resulting in significant gains compared to baseline methods.

Two-dimensional materials-based probabilistic synapses and reconfigurable neurons for measuring inference uncertainty using Bayesian neural networks

Artificial neural networks have demonstrated superiority over traditional computing architectures in tasks such as pattern classification and learning. However, they do not measure uncertainty in predictions, and hence they can make wrong predictions with high confidence, which can be detrimental for many mission-critical applications. In contrast, Bayesian neural networks (BNNs) naturally include such uncertainty in their model, as the weights are represented by probability distributions (e.g. Gaussian distribution). Here we introduce three-terminal memtransistors based on two-dimensional (2D) materials, which can emulate both probabilistic synapses as well as reconfigurable neurons. The cycle-to-cycle variation in the programming of the 2D memtransistor is exploited to achieve Gaussian random number generator-based synapses, whereas 2D memtransistor based integrated circuits are used to obtain neurons with hyperbolic tangent and sigmoid activation functions. Finally, memtransistor-based synapses and neurons are combined in a crossbar array architecture to realize a BNN accelerator for a data classification task.

Relay-Assisted Uplink Transmission Design of URLLC Packets

With the emergence and development of mission-critical applications, the design of uplink URLLC transmission has become one of the issues of concern. In this article, we consider the ultrareliable uplink transmission design between multiple robots and a central controller in a smart factory with stringent delay requirements while multiple relays are deployed for cooperative transmission. Subject to the throughput and reliability requirements, a relay-assisted two-phase transmission protocol is proposed aiming at total transmit power minimization by jointly optimizing the decoding error probability, relay selection, resource block (RB) assignment, and transmit power allocation. To support the mission-critical applications in Internet of Things (IoT) with diverse throughput targets and make full use of RBs, we investigate the optimization problem under the single-RB allocation and multi-RB allocation schemes. The problems in these two cases have an analogous structure and can be solved with a unified framework. In the solution framework, we present the optimal design solved by the nonconvex penalty (NCP)- and quadratic penalty (QP)-based successive convex approximation (SCA) algorithms and the corresponding low-complexity design with near-optimal settings of decoding error probabilities. Numerical results demonstrate the effectiveness of the proposed penalty-based iterative algorithms and confirm that the near-optimal design only causes minor power performance loss compared to the optimal design. The power performance gap under these two allocation schemes and the impact of system parameters are revealed and analyzed.

Dynamic mode selection and resource allocation approach for 5G-vehicle-to-everything (V2X) communication using asynchronous federated deep reinforcement learning method

5G vehicle-to-everything (V2X) connectivity is crucial to enable future complex vehicular networking environment for enabling intelligent transportation systems (ITS). But, for mission critical applications like safety applications, unreliable vehicle-to-vehicle (V2V) connections and heavy signaling overheads in centralized resource distribution methods are becoming key obstacles. This work discusses the popular optimization issue of the selection of transmission mode and the allocation of resources blocks for 5G-V2X communication scenario. The stated problem is conceived as a Markov decision-making mechanism, and a Decentralized Deep reinforcement Learning (DRL) algorithm is presented to optimize the aggregate potential in terms of channel capacity of vehicle-to-infrastructure users while fulfilling the latency and reliability constraints of V2V communication link sets. In addition, considering training limitation of local DRL models, a two-timed synchronous federated DRL algorithm is used for making system robust. Therefore, we use two-timescale asynchronous federated deep reinforcement learning algorithm, i.e. Large-scale model and small- scale model. In large-scale model a graph-centered vehicle clustering is done to form the cluster of neighboring vehicles on a large timescale, whereas in small timescale model the vehicles in the similar cluster are used to train using robust global asynchronous federated deep reinforcement learning algorithm. The effects of outage threshold and vehicular density with respect to the network performance is presented. The simulation findings have shown that the proposed work outperforms the other previous state of the art works. The overall preeminence and convergence of the proposed work is verified.

Point cloud based online detection of geometric defects for the certification of additively manufactured mechanical metamaterials

Unlike conventional materials, the properties of a mechanical metamaterial are governed by its periodically-arranged unit cells. It is critical to precisely realize the designed unit cell geometry so that desired properties can be achieved. Owing to its high-level freedom in design and fabrication, additive manufacturing (AM) has been increasingly leveraged for the production of mechanical metamaterials. However, geometric defects largely exist in AM products. The gap between “as-designed” and “as-built” unit cell geometries will compromise the properties of the printed metamaterial and even cause safety hazards for mission-critical applications. This study develops a novel framework that harnesses in-situ point cloud sensing and analytics for the detection and characterization of geometric defects in additively manufactured mechanical metamaterials. Specifically, upon the printing of each layer, a point cloud is obtained to capture the geometries of unit cells. A recurrence plot based approach is developed to characterize how each printed unit cell departs from the as-designed counterpart. After that, we integrate low-rank tensor decomposition with one-class classification to determine whether the unit cells on the printed layer are associated with geometric defects. Results of simulations and real-world experiments have shown that the developed framework effectively handles the complexity of mechanical metamaterials and characterizes geometric defects for online quality assurance.

Condition monitoring of power module using S-parameters, TDR, and TDT

Condition monitoring of power electronics is gaining interest as power electronics expends to mission-critical applications. This paper offers a preliminary experimental study of the viability of using S-parameters and time-domain reflectometry measurements to monitor the degradation of a power module. To this end, measurements were performed on a standard high current power module which was artificially aged by cutting wire bonds one by one. The study demonstrates a clear trend in the evolution of measured parameters, and thereby the possibility to monitor the power module degradation under the specific test conditions. This opens a new condition monitoring technology for power electronics systems.