Network Solution Research Articles

Employing Robotics and Deep Learning in Underground Leak Detection

Leaks in water distribution networks (WDNs) produce significant economic losses. These leaks from underground pipelines affect the surrounding environment in different ways that can be detected using various technologies. This article introduces an unmanned ground vehicle (UGV) equipped with an infrared temperature sensor to remotely detect thermal anomalies on the surface caused by underground leaking pipelines. An MLX90614 low-cost thermopile infrared sensor was proposed to trace the surface temperature above leaking pipelines and record the corresponding position of each reading. Two positioning techniques were tested independently: a satellite navigation system and odometry using a magnetic encoder. Raw data from the temperature sensor along with the corresponding locations were recorded on a MicroSD card using an Arduino Uno Board through analog-to-digital converters (ADCs) and serial peripheral interface (SPI) bus. Experimental work showed the ability of the robot in detecting thermal anomalies caused by leaks accurately with the required trace resolution. Finally, a 2-D convolutional neural network (CNN) solution is introduced for distinguishing true detections from false alarms.

Enhancing Renal Tumor Detection: Leveraging Artificial Neural Networks in Computed Tomography Analysis.

BACKGROUND Renal cell carcinoma is one of the most common cancers in Europe, with a total incidence rate of 18.4 cases per 100 000 population. There is currently significant overdiagnosis (11% to 30.9%) at times of planned surgery based on radiological studies. The purpose of this study was to create an artificial neural network (ANN) solution based on computed tomography (CT) images as an additional tool to improve the differentiation of malignant and benign renal tumors and to aid active surveillance. MATERIAL AND METHODS A retrospective study based on CT images was conducted. Axial CT images of 357 renal tumor cases were collected. There were 265 (74.2%) cases histologically proven to be malignant, while 34 (9.5%) cases were benign. Radiologists diagnosed 58 (16.3%) cases as angiomyolipoma (AML), based on characteristic appearance, not confirmed histopathologically. For ANN training, the arterial CT phase images were used. A total of 7207 arterial-phase images were collected, then cropped and added to the database with the associated diagnosis. For the test dataset (ANN validation), 38 cases (10 benign, 28 malignant) were chosen by subgroup randomization to correspond to statistical tumor type distribution. The VGG-16 ANN architecture was used in this study. RESULTS Trained ANN correctly classified 23 out of 28 malignant tumors and 8 out of 10 benign tumors. Accuracy was 81.6% (95% confidence interval, 65.7-92.3%), sensitivity was 82.1% (63.1-93.9%), specificity was 80.0% (44.4-97.5%), and F1 score was 86.8% (74.7-94.5%). CONCLUSIONS The created ANN achieved promising accuracy in differentiating benign vs malignant renal tumors.

Evaluation of Physics-Informed Neural Network Solution Accuracy and Efficiency for Modeling Aortic Transvalvular Blood Flow

Physics-Informed Neural Networks (PINNs) are a new class of machine learning algorithms that are capable of accurately solving complex partial differential equations (PDEs) without training data. By introducing a new methodology for fluid simulation, PINNs provide the opportunity to address challenges that were previously intractable, such as PDE problems that are ill-posed. PINNs can also solve parameterized problems in a parallel manner, which results in favorable scaling of the associated computational cost. The full potential of the application of PINNs to solving fluid dynamics problems is still unknown, as the method is still in early development: many issues remain to be addressed, such as the numerical stiffness of the training dynamics, the shortage of methods for simulating turbulent flows and the uncertainty surrounding what model hyperparameters perform best. In this paper, we investigated the accuracy and efficiency of PINNs for modeling aortic transvalvular blood flow in the laminar and turbulent regimes, using various techniques from the literature to improve the simulation accuracy of PINNs. Almost no work has been published, to date, on solving turbulent flows using PINNs without training data, as this regime has proved difficult. This paper aims to address this gap in the literature, by providing an illustrative example of such an application. The simulation results are discussed, and compared to results from the Finite Volume Method (FVM). It is shown that PINNs can closely match the FVM solution for laminar flow, with normalized maximum velocity and normalized maximum pressure errors as low as 5.74% and 9.29%, respectively. The simulation of turbulent flow is shown to be a greater challenge, with normalized maximum velocity and normalized maximum pressure errors only as low as 41.8% and 113%, respectively.

Machine Learning Algorithms for IoT Security

Worldwide Internet of Things has been rapidly evolved within smart devices that interact with each other via machine to machine communications. It is revolutionizing the IT market and will have deep, economic and social impact on our lives. The interconnecting devices in IoT networks usually become targets for cyber-attacks. In this regard, far-reaching efforts have been made to address the security and privacy issues in IoT networks primarily through symmetric and asymmetric cryptographic approaches. Due to resource constraints, heterogeneity, massive real time data generated by the IoT devices the traditional cryptographic algorithm become insufficient to encompass the entire security to the IoT devices. Therefore, Machine Learning (ML) and Deep Learning (DL) techniques, which are able to provide embedded intelligence in the IoT devices and networks, are leveraged to cope with different security problems. In this paper, we systematically review the security algorithms, attack parameters, and the current security solutions for the IoT networks.

Intelligent multichannel cross-layer framework for enhanced energy-efficiency in 6G-IoT wireless networks

The sixth-generation (6G) communication technology is expected to enable a fully-connected world with enhanced wireless connectivity, accessibility, reliability, and performance. 6G systems will be critical in addressing the massive-connectivity requirements for Internet-of-Things (IoT) networks. Cognitive radio (CR) technology is considered a promising solution in 6G networks that can provide tremendous spectrum opportunities to support large-scale IoT deployments. Due to the IoT’s energy-constrained and massively connected nature, existing CR-based communication protocols cannot be directly implemented in 6G-IoT networks. This is because they are usually designed to enhance spectrum-utilization in networks with finite users. Therefore, energy-efficient protocols are required to support the massive-connectivity requirement for energy-constrained IoT nodes. Non-persistent Carrier-Sense-Multiple-Access (CSMA)-based protocols are recognized as energy-effective spectrum-access paradigms for networks with massive users. This paper proposes a novel energy-efficient multi-channel cross-layer MAC framework that utilizes a non-persistent CSMA protocol in CR-enabled 6G-IoT networks. Based on a joint adaptation of the physical and MAC layer parameters, our framework aims to improve IoT networks’ energy efficiency (EE). Specifically, we formulate and solve the per-bit EE maximization problem subject to several design constraints. Numerical results show that our multi-channel cross-layer framework enhances network EE by up to 50% compared to a reference single-channel cross-layer design.

DT-RRNS: Routing Protocol Design for Secure and Reliable Distributed Smart Sensors Communication Systems

A smart city has a complex hierarchical communication system with various components. It must meet the requirements of fast connection, reliability, and security without data compromise. Internet of Things technology is widely used to provide connectivity and control solutions for smart sensors and other devices using heterogeneous networking technologies. In this paper, we propose a routing solution for Wireless Sensor Networks (WSN) and Mobile Ad hoc NETworks (MANET) with increasing speed, reliability, and sufficient security. Many routing protocols have been proposed for WSNs and MANETs. We combine the Secret Sharing Schemes (SSS) and Redundant Residual Number Systems (RRNS) to provide an efficient mechanism for a Distributed dynamic heterogeneous network Transmission (DT) with new security and reliability routing protocol (DT-RRNS). We analyze the concept of data transmission based on RRNS that divides data into smaller encoded shares and transmits them in parallel, protecting them from attacks on routes by adaptive multipath secured transmission and providing self-correcting properties that improve the reliability and fault tolerance of the entire system.

LwHBench: A low-level hardware component benchmark and dataset for Single Board Computers

In today’s computing environment, where Artificial Intelligence (AI) and data processing are moving toward the Internet of Things (IoT) and Edge computing paradigms, benchmarking resource-constrained devices is a critical task to evaluate their suitability and performance. Between the employed devices, Single-Board Computers arise as multi-purpose and affordable systems. The literature has explored Single-Board Computers performance when running high-level benchmarks specialized in particular application scenarios, such as AI or medical applications. However, lower-level benchmarking applications and datasets are needed to enable new Edge-based AI solutions for network, system and service management based on device and component performance, such as individual device identification. Thus, this paper presents LwHBench, a low-level hardware benchmarking application for Single-Board Computers that measures the performance of CPU, GPU, Memory and Storage taking into account the component constraints in these types of devices. LwHBench has been implemented for Raspberry Pi devices and run for 100 days on a set of 45 devices to generate an extensive dataset that allows the usage of AI techniques in scenarios where performance data can help in the device management process. Besides, to demonstrate the inter-scenario capability of the dataset, a series of AI-enabled use cases about device identification and context impact on performance are presented as exploration of the published data. Finally, the benchmark application has been adapted and applied to an agriculture-focused scenario where three RockPro64 devices are present.

RheologyNet: A physics-informed neural network solution to evaluate the thixotropic properties of cementitious materials

Thixotropic behaviors can be predicted by rheological partial differential equations (PDEs) of cementitious materials. The ability to solve the rheological PDEs of viscous fluids accurately and efficiently has become an emerging interest in research. However, due to the growing number of parameters in rheological constitutive equations and the non-ideal behavior of materials from experiments, solving the rheological PDEs becomes computationally costive and error-prone. We propose a physics-informed neural network (PINN)-based framework, RheologyNet, as a surrogate solution to predict the general thixotropic behavior of cementitious materials. The complex PDEs are embedded in the well-designed RheologyNet architecture to link macroscopic viscous flow behaviors and microstructural changes. Numerical experiments suggested that RheologyNet can accurately and efficiently predict the rheological properties of cementitious materials compared to the traditional Fully-connected Neural Network (FNN) and mechanistic Finite Element Analysis (FEA). Particularly, RheologyNet demonstrated great promise for simulating history-dependent thixotropic behaviors.

Flexible handover solution for vehicular ad-hoc networks based on software defined networking and fog computing

<p>Vehicular ad-hoc networks (VANET) suffer from dynamic network environment and topological instability that caused by high mobility feature and varying vehicles density. Emerging 5G mobile technologies offer new opportunities to design improved VANET architecture for future intelligent transportation system. However, current software defined networking (SDN) based handover schemes face poor handover performance in VANET environment with notable issues in connection establishment and ongoing communication sessions. These poor connectivity and inflexibility challenges appear at high vehicles speed and high data rate services. Therefore, this paper proposes a flexible handover solution for VANET networks by integrating SDN and fog computing (FC) technologies. The SDN provides global knowledge, programmability and intelligence functions for simplified and efficient network operation and management. FC, on the other hand, alleviates the core network pressure by providing real time computation and transmission functionalities at edge network to maintain the demands of delay sensitive applications. The proposed solution overcomes frequent handover challenges and reduces the processing overhead at core network. Moreover, the simulation evaluation shows significant handover performance improvement of the proposed solution compared to current SDN based schemes, especially in terms of handover latency and packet loss ratio under various simulation environments.</p>

Adaptive Relay Selection Strategy in Underwater Acoustic Cooperative Networks: A Hierarchical Adversarial Bandit Learning Approach

Relay selection solutions for underwater acoustic cooperative networks suffer significant performance degradation as they fail to adapt to incomplete information, noisy interference and overwhelming dynamics. To address this challenge, a hierarchical adversarial multi-armed bandit learning framework by proposing an online reward estimation layer is designed to improve adaptive relay decision control. In online reward estimation layer, adaptive Kalman filter estimator is developed to properly handle noisy observation to support accurate reward. Meanwhile, an online predict mechanism is projected for all relays to enrich learning information. Furthermore, based on estimate error variance, an adaptive exploration structure is developed to accelerate the balance between exploration and exploitation. All gathered information are exploited to learn relay quality for the decision-making. Accordingly, we present a Hierarchical Adversarial Bandit Learning (HABL) algorithm to fully exploit the heuristic interaction between the hierarchical framework. HABL integrates reward estimation, information prediction, adaptive exploration and decision making carefully in a holistic algorithm to maximize the learning efficiency. Thereby, the HABL-based relay selection algorithm has higher system throughput and lower communication cost. Further, we rigorously analyze the convergence of HABL algorithm and give its upper bound on the cumulative regret. Finally, extensive simulations elucidate the effectiveness of the HABL.

Backscatter‐assisted Non‐orthogonal multiple access network for next generation communication

AbstractNon‐orthogonal multiple access (NOMA) technique introduces spectrum cooperation among different users and devices, which improves spectrum efficiency significantly. Energy‐limited devices benefit from the backscatter (BAC) technique to transmit signals without extra energy consumption. The combination of NOMA and BAC provides a promising solution for Internet of Things (IoT) networks, where massive devices simultaneously transmit and receive signals. This study investigates a system model with two NOMA downlink users and an uplink device. The aim is to maximise the data rate of the uplink device by optimising the power allocation coefficient and the backscattering coefficient. Meanwhile the quality of service requirements of two NOMA users are guaranteed. The closed‐form solution of two optimisation variables is derived, and an alternating algorithm is also proposed to solve the formulated optimisation problem efficiently. The proposed system verifies the feasibility of IoT devices being added into existing networks and provides a promising solution for wireless communication networks in the future.

Energy efficient and multi-hop routing for constrained wireless sensor networks

Wireless sensor network (WSN) technique has advanced in several applications, however, the environment has significant energy and security challenges. Therefore, this research proposes a Multi-Hop, Trivial, as well as Protected Routing Solution for Constrained Wireless Sensor Networks. The Chaotic Particle-swarm Krill Herd (CPKH) method, which includes chaotic theory with accelerated PSO (APSO) as a mutation operator into the krill herd method, is used to first choose the energy-efficient cluster heads. Then, to select the optimal path this research proposed a novel Self-Adaptive Step Glow Worm Swarm Optimization (SASGWS) Algorithm. Following that, the Hamming Residue Technique (HRT) is utilized to counteract the malicious attacks in the WSN. The proposed technology, which could result in increased power efficiency as well as high bandwidth, analyses system status on demand as well as dynamically identifies system hazards.

Deep learning for SDN-enabled campus networks: proposed solutions, challenges and future directions

PurposeThis study explores challenges facing the applicability of deep learning (DL) in software-defined networks (SDN) based campus networks. The study intensively explains the automation problem that exists in traditional campus networks and how SDN and DL can provide mitigating solutions. It further highlights some challenges which need to be addressed in order to successfully implement SDN and DL in campus networks to make them better than traditional networks.Design/methodology/approachThe study uses a systematic literature review. Studies on DL relevant to campus networks have been presented for different use cases. Their limitations are given out for further research.FindingsFollowing the analysis of the selected studies, it showed that the availability of specific training datasets for campus networks, SDN and DL interfacing and integration in production networks are key issues that must be addressed to successfully deploy DL in SDN-enabled campus networks.Originality/valueThis study reports on challenges associated with implementation of SDN and DL models in campus networks. It contributes towards further thinking and architecting of proposed SDN-based DL solutions for campus networks. It highlights that single problem-based solutions are harder to implement and unlikely to be adopted in production networks.

Linear Algebraic Systems Neural Network Solution. Part 1

In recent years, neural networks have become increasingly popular due to their versatility in solving complex problems. One area of interest is their application in solving linear algebraic systems, especially those that are ill-conditioned. The solutions of such systems are highly sensitive to small changes in their coefficients, leading to unstable solutions. Therefore, solving these types of systems can be challenging and require specialized techniques. This article explores the use of neural network methodologies for solving linear algebraic systems, focusing on ill-conditioned systems. The primary goal is to develop a model capable of directly solving linear equations and to evaluate its performance on a range of linear equation sets, including ill-conditioned systems. To tackle this problem, neural network implementing iterative algorithm was built. Error function of linear algebraic system is minimized using stochastic gradient descent. This model doesn’t require extensive training other than tweaking learning rate for particularly large systems. The analysis shows that the suggested model can handle well-conditioned systems of varying sizes, although for systems with large coefficients some normalization is required. Improvements are necessary for effectively solving ill-conditioned systems, since researched algorithm is shown to be not numerically stable. This research contributes to the understanding and application of neural network techniques for solving linear algebraic systems. It provides a foundation for future advances in this field and opens up new possibilities for solving complex problems. With further research and development, neural network models can become a powerful tool for solving ill-conditioned linear systems and other related problems.

Distributed decentralized EKF for very large-scale networks with application to satellite mega-constellations navigation

The design of a decentralized and distributed filtering solution for large-scale networks of interconnected systems is addressed considering (i) generic nonlinear dynamics and (ii) generic coupled nonlinear outputs in a generic, possibly time-varying, topology. The local filters, which follow the structure of the extended Kalman filter, are implemented in each system, which estimates its own state exclusively. To be suitable for the heavily restricted implementation to very large-scale systems, a novel algorithm is proposed, which: (i) does not rely on instantaneous data transmission; (ii) allows local communication exclusively; and (iii) requires computational, memory, and data transmission resources for each system that do not scale with the dimension of the network. The scalability of the proposed algorithm allows for its application to the cooperative localization problem of very large-scale systems. In particular, it is applied herein to the on-board position estimation problem of LEO mega-constellations using GNSS featuring numerical simulations for the Starlink constellation.

Deep Edge Detection Methods for the Automatic Calculation of the Breast Contour.

Breast cancer conservative treatment (BCCT) is a form of treatment commonly used for patients with early breast cancer. This procedure consists of removing the cancer and a small margin of surrounding tissue, while leaving the healthy tissue intact. In recent years, this procedure has become increasingly common due to identical survival rates and better cosmetic outcomes than other alternatives. Although significant research has been conducted on BCCT, there is no gold-standard for evaluating the aesthetic results of the treatment. Recent works have proposed the automatic classification of cosmetic results based on breast features extracted from digital photographs. The computation of most of these features requires the representation of the breast contour, which becomes key to the aesthetic evaluation of BCCT. State-of-the-art methods use conventional image processing tools that automatically detect breast contours based on the shortest path applied to the Sobel filter result in a 2D digital photograph of the patient. However, because the Sobel filter is a general edge detector, it treats edges indistinguishably, i.e., it detects too many edges that are not relevant to breast contour detection and too few weak breast contours. In this paper, we propose an improvement to this method that replaces the Sobel filter with a novel neural network solution to improve breast contour detection based on the shortest path. The proposed solution learns effective representations for the edges between the breasts and the torso wall. We obtain state of the art results on a dataset that was used for developing previous models. Furthermore, we tested these models on a new dataset that contains more variable photographs and show that this new approach shows better generalization capabilities as the previously developed deep models do not perform so well when faced with a different dataset for testing. The main contribution of this paper is to further improve the capabilities of models that perform the objective classification of BCCT aesthetic results automatically by improving upon the current standard technique for detecting breast contours in digital photographs. To that end, the models introduced are simple to train and test on new datasets which makes this approach easily reproducible.

Neural ordinary differential equation for sequential optimal design of fatigue test under accelerated life test analysis

The literature on fatigue analysis can be classified into parametric or analytic approaches that try to model the fatigue data with a specific distribution, such as the optimal sequential Accelerated Life Test (ALT), considering the fatigue life cycle and stress amplitude. To the best of our knowledge, no work incorporates the accelerated lifecycle distribution of fatigue data into the parametric approach, nor does it incorporate the complex relationships in the elastic–plastic behavior of the material in the ALT models using the sequential optimal test design. In this work, we define an optimization model that takes both parametric and analytic solutions into account and minimizes the negative log-likelihood of the ALT model when the fatigue lifecycle follows a lognormal distribution for several constraints extracted from physical attributes of elastic–plastic models and assumptions of the ALT approach, where model-based optimization is sequentially updated. We utilized a model-based deep neural network solution based on the differential equation of the analytical model to solve the optimization problem. Our simulation results based on empirical data prove the practical implementation of our approach and validate the result for obtaining the optimal test plan and estimated parameters of the ALT and elastic–plastic model.

IoT-based Hybrid Wireless Network for Tourist Boat Tracking towards Smart Cities

Moving and transporting by canoe and boat on rivers and canals is a cultural feature of the Mekong Delta and plays an important role in the economy and society. However, the management and use of equipment to support the monitoring of waterway transport vehicles in this area has yet to receive adequate investment and attention. Given the complicated evolution of the COVID-19 epidemic, it is critical to strengthen oversight of inland waterway management, as well as freight and passenger transportation. This paper presents the design and implementation of an IoT-based support system for managing and monitoring passenger ships and tourism activities in smart cities. This study proposes a hybrid wireless communication network solution that takes advantage of the strengths of LoRa and Zigbee wireless communication technologies, as well as telecommunication networks, to ensure that the system has a wide operating range of several kilometers, low power consumption, and can be deployed in areas where telecommunications are not available. Aside from tracking the journey and managing information about vehicles, drivers, and passengers, the system also aids in the collection of environmental parameters along river routes according to the travel route. An experimental evaluation of the system's operation was carried out for the tourist boat route between two famous tourist sites, Ninh Kieu Key and Cai Rang floating market in Can Tho city, Vietnam.

Faulty branch identification in passive optical networks using machine learning

Passive optical networks (PONs) have become a promising broadband access network solution thanks to their wide bandwidth, low-cost deployment and maintenance, and scalability. To ensure a reliable transmission, and to meet service level agreements, PON systems have to be monitored constantly in order to quickly identify and localize network faults and thus reduce maintenance costs, minimize downtime, and enhance quality of service. Typically, a service disruption in a PON system is mainly due to fiber cuts and optical network unit (ONU) transmitter/receiver failures. When the ONUs are located at different distances from the optical line terminal, the faulty ONU or branch can be identified by analyzing the recorded optical time domain reflectometry (OTDR) traces. OTDR is a technique commonly used for monitoring of fiber optic links. However, faulty branch isolation becomes very challenging when the reflections originate from two or more branches with similar length overlap, which makes it very hard to discriminate the faulty branches given the global backscattered signal. Recently, machine learning (ML)-based approaches have shown great potential for managing optical faults in PON systems. Such techniques perform well when trained and tested with data derived from the same PON system. But their performance may severely degrade if the PON system (adopted for the generation of the training data) has changed, e.g., by adding more branches or varying the length difference between two neighboring branches, etc. A re-training of the ML models has to be conducted for each network change, which can be time consuming. In this paper, to overcome the aforementioned issues, we propose a generic ML approach trained independently of the network architecture for identifying the faulty branch in PON systems given OTDR signals for the cases of branches with close lengths. Such an approach can be applied to an arbitrary PON system without requiring to be re-trained for each change of the network. The proposed approach is validated using experimental data derived from the PON system.

Genetic algorithm‐based partial charging schedule of rechargeable sensor networks

SummaryThe use of rechargeable sensors is a promising solution for wireless sensor networks. On this type of network, mobile charging vehicles (MC) are used for charging sensors using wireless energy transfer (WET) technology. In on‐demand charging, a sensor transmits a charging request to the service station, and the MC visits the sensor to transfer energy. The key disadvantages of utilizing MC‐based WET are its high energy expenditure rate due to mobility, long service time, and slow charging rate. Because of these reasons, sensors deplete their energy and become dead before the MC reaches the requesting nodes to recharge. We have adapted a genetic algorithm‐based partial charging scheme to serve the charging requests. Our objective is to improve the survival ratio of the network. Using comprehensive simulations, we analyze the performance of our proposed method and compare it to two other existing approaches. The simulation results demonstrate that our proposed algorithm improves the survival ratio by up to 20 % by developing a dynamic energy threshold function for transmitting charging requests from the sensors and a partial charging schedule using a genetic algorithm.