Flexible Network Architecture Research Articles

Microsoft applications of 6G in V2X

Abstract. With the rapid advancement of intelligent transportation systems and autonomous driving technologies, 6G networks, as a key technology for future communications, are set to bring trans-formative changes to V2X (Vehicle-to-Everything) communication. This paper explores the application prospects of 6G in V2X, with a focus on the critical technological support 6G provides to vehicular networks. The high transmission rates and ultra-low latency of 6G will significantly enhance real-time interactions between vehicles and between vehicles and infrastructure, improving traffic safety and efficiency. Additionally, 6G's broad connectivity and flexible network architecture will support a greater number of simultaneous device connections, facilitating the widespread adoption of intelligent transportation systems. However, 6G faces challenges in V2X applications, including security issues, privacy protection, and internet power supply concerns. The paper analyzes these challenges, proposes corresponding solutions, and envisions the future development of 6G technology in the V2X domain.

Regulatory and spectrum policy challenges for combined airspace and non-terrestrial networks

The recent advancements in the aviation and space industries facilitate new types of users in the sky, e.g., electrical vertical take-off and landing (eVTOL) aircraft. To unlock the full potential of these innovations, it is crucial to create interconnected three-dimensional networks that integrate airspace and non-terrestrial networks (NTNs) with their terrestrial counterparts, also known as Combined Airspace and Non-Terrestrial Networks (ASN). Combined ASN needs a flexible and adaptive network architecture with multiple, and partly converging technologies, such as air-to-ground, satellite, and high-altitude platforms, with a focus to cover both ground and aerial users. In addition to technical challenges, spectrum policy and regulatory aspects will affect the wireless network design and management schemes in three-dimensional space. Hence, this paper introduces regulatory and spectrum policy challenges posed by the development of combined ASN. This paper investigates a hypothetical urban air mobility use case with an eVTOL aircraft that operates as a flying taxi.

Optimizing personalized treatments for targeted patient populations across multiple domains.

Learning individualized treatment rules (ITRs) for a target patient population with mental disorders is confronted with many challenges. First, the target population may be different from the training population that provided data for learning ITRs. Ignoring differences between the training patient data and the target population can result in sub-optimal treatment strategies for the target population. Second, for mental disorders, a patient's underlying mental state is not observed but can be inferred from measures of high-dimensional combinations of symptomatology. Treatment mechanisms are unknown and can be complex, and thus treatment effect moderation can take complicated forms. To address these challenges, we propose a novel method that connects measurement models, efficient weighting schemes, and flexible neural network architecture through latent variables to tailor treatments for a target population. Patients' underlying mental states are represented by a compact set of latent state variables while preserving interpretability. Weighting schemes are designed based on lower-dimensional latent variables to efficiently balance population differences so that biases in learning the latent structure and treatment effects are mitigated. Extensive simulation studies demonstrated consistent superiority of the proposed method and the weighting approach. Applications to two real-world studies of patients with major depressive disorder have shown a broad utility of the proposed method in improving treatment outcomes in the target population.

A Survey an Optimized Dense CNN Model for Recognizing Deepfake Images

Deepfake detection relies on a deep learning model. Deepfake content is generated using artificial intelligence and machine learning techniques to swap one person’s face with another’s in images. These altered images are certain to have a significant impact on society. Deepfakes utilize advanced technologies such as machine learning (ML) and deep learning (DL) to develop automated techniques for generating deceptive content. The model is trained using the DFDC (Deepfake Detection Challenge) dataset, which includes 1, 00,000 videos comprising both real and fake content. This survey examines recent progress in deep learning techniques for detecting deepfake images, highlighting their growing significance in today’s digital landscape. The paper outlines the issues arising from deepfakes, explores the techniques for generating deceptive content, and analyzes various deep learning models employed in deepfake detection, such as convolutional neural networks (CNN’s), MTCNN (Multi-task CNN), and Facial Landmark. It emphasizes the ongoing battle between the progression of deepfakes and the evolution of detection methods, underscoring the need for advanced and flexible neural network architectures to effectively curb the dissemination of deceptive information.

A robust adapted Flexible Parallel Neural Network architecture for early prediction of lithium battery lifespan

Early prediction of End of Life (EPEOL) is crucial for improving lithium battery efficiency and lifespan. Traditional fixed-architecture neural networks often suffer from underfitting or overfitting due to diverse data distributions. To address this, we propose the Flexible Parallel Neural Network (FPNN). This model integrates modules like InceptionBlock, 3D CNN, 2D CNN, and dual-stream networks. By effectively extracting electrochemical features from video-format data through the 3D CNN and achieving multi-scale feature abstraction with InceptionBlock, FPNN ensures effective module coordination. The model can adaptively adjust the number of InceptionBlocks to handle tasks of varying complexity. Experimental results on the MIT dataset show that FPNN achieves MAPE values of 1.26%, 0.41%, 0.37%, 0.33%, 0.32%, 0.32%, 0.31%, 0.31%, 0.22%, and 0.34% using the first 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100 cycle data, respectively. The interpretability of FPNN is reflected in its structural design and flexible unit choices, providing a basis for model interpretation. Comprising multiple modules, FPNN enables smooth feature extraction from electrochemical data through collaborative interaction. The diverse branching structure of the flexible units allows the model to capture features at different scales, learning richer information. Our approach offers a precise, adaptable, and easy-to-understand solution for EPEOL, opening new possibilities in battery health monitoring.

Deployment of efficient MANET testbed using aggregation based archive population optimization

In today’s 6G era, Mobile ad hoc networks (MANETs) have been enhanced by rapid technological advancement in the wireless communication industry to better support a wide range of domains, including military operations, emergency operations, urban settings, and natural crisesmanagement. In MANET, self-organizing mobile nodes collaborate to build a flexible network architecture. With a MANET, data must transit through numerous intermediate nodes even before reaches its destination node. Local link connectivity is essential for the establishment and preservation of routes. To decrease energy usage, these findings suggest the Aggregation-based Archive Population Optimization(AAPO) along with Ad-hoc On-demand Distance Vector (AODV) Routing Protocol. For both local and global optimal routes, the proposed optimized modelgives top priority. There existtwo different types of rules used by AAPO to evaluate the quality of a route before using it for data transmission. Instead of relying on just one path for transmitting data, AAPO leverages many paths. Also, it minimizes the issue of the network nodes being suddenly inaccessible, which eliminates interruptions in transmissions. However, the suggested optimal routing system considers mobility and energy availability when responding to queries, resulting in significant performance improvements, utilizing 42.69 % of the scenario’s power and functioning at 208.6 kbps with an average PDR of 87.1 %. Also, detailed simulations are conducted using the Matlab (R2021b)software to assess the suggested approach. Furthermore, the suggested protocol outperforms the current methods in terms of effectiveness.

Distribution-informed and wavelength-flexible data-driven photoacoustic oximetry.

Photoacoustic imaging (PAI) promises to measure spatially resolved blood oxygen saturation but suffers from a lack of accurate and robust spectral unmixing methods to deliver on this promise. Accurate blood oxygenation estimation could have important clinical applications from cancer detection to quantifying inflammation. We address the inflexibility of existing data-driven methods for estimating blood oxygenation in PAI by introducing a recurrent neural network architecture. We created 25 simulated training dataset variations to assess neural network performance. We used a long short-term memory network to implement a wavelength-flexible network architecture and proposed the Jensen-Shannon divergence to predict the most suitable training dataset. The network architecture can flexibly handle the input wavelengths and outperforms linear unmixing and the previously proposed learned spectral decoloring method. Small changes in the training data significantly affect the accuracy of our method, but we find that the Jensen-Shannon divergence correlates with the estimation error and is thus suitable for predicting the most appropriate training datasets for any given application. A flexible data-driven network architecture combined with the Jensen-Shannon divergence to predict the best training data set provides a promising direction that might enable robust data-driven photoacoustic oximetry for clinical use cases.

A Flexible Infrastructure-Sharing 5G Network Architecture Based on Network Slicing and Roaming

The sharing of mobile network infrastructure has become a key topic with the introduction of 5G due to the high costs of deploying such infrastructures, with neutral host models coupled with features such as network function virtualization (NFV) and network slicing emerging as viable solutions for the challenges in this area. With this in mind, this work presents the design, implementation, and test of a flexible infrastructure-sharing 5G network architecture capable of providing services to any type of client, whether an operator or not. The proposed architecture leverages 5G’s network slicing for traffic isolation and compliance with the policies of different clients, with roaming employed for the authentication of users of operator clients. The proposed architecture was implemented and tested in a simulation environment using the UERANSIM and Open5GS open-source tools. Qualitative tests successfully validated the authentication and the traffic isolation features provided by the slices for the two types of clients. Results also demonstrate that the proposed architecture has a positive impact on the performance of the neutral host network infrastructure, achieving 61.8%-higher throughput and 96.8%-lower packet loss ratio (PLR) in a scenario sharing the infrastructure among four clients and eight users when compared to a single client with all the network resources.

Case-Base Neural Network: Survival analysis with time-varying, higher-order interactions

In the context of survival analysis, data-driven neural network-based methods have been developed to model complex covariate effects. While these methods may provide better predictive performance than regression-based approaches, not all can model time-varying interactions and complex baseline hazards. To address this, we propose Case-Base Neural Networks (CBNNs) as a new approach that combines the case-base sampling framework with flexible neural network architectures. Using a novel sampling scheme and data augmentation to naturally account for censoring, we construct a feed-forward neural network that includes time as an input. CBNNs predict the probability of an event occurring at a given moment to estimate the full hazard function. We compare the performance of CBNNs to regression and neural network-based survival methods in a simulation and three case studies using two time-dependent metrics. First, we examine performance on a simulation involving a complex baseline hazard and time-varying interactions to assess all methods, with CBNN outperforming competitors. Then, we apply all methods to three real data applications, with CBNNs outperforming the competing models in two studies and showing similar performance in the third. Our results highlight the benefit of combining case-base sampling with deep learning to provide a simple and flexible framework for data-driven modeling of single event survival outcomes that estimates time-varying effects and a complex baseline hazard by design. An R package is available at https://github.com/Jesse-Islam/cbnn.

Self-assembled high polypyrrole loading flexible paper-based electrodes for high-performance supercapacitors

Despite the intriguing features of freestanding flexible electronic devices, such as their binder-free nature and cost-effectiveness, the limited loading capacity of active material poses a challenge to achieving practical high-performance flexible electrodes. We propose a novel approach that integrates multiple self-assembly and in-situ polymerization techniques to fabricate a high-loading paper-based flexible electrode (MXene/Polypyrrole/Paper) with exceptional areal capacitance. The approach enables polypyrrole to form a porous conductive network structure on the surface of paper fiber through MXene grafting via hydrogen bonding and electrostatic interaction, resulting in an exceptionally high polypyrrole loading of 10.0 mg/cm2 and a conductivity of 2.03 S/cm. Moreover, MXene-modified polypyrrole paper exhibits a more homogeneous pore size distribution ranging from 5 to 50 μm and an increased specific surface area of 3.11 m2/g. Additionally, we have optimized in-situ polymerization cycles for paper-based supercapacitors, resulting in a remarkable areal capacitance of 2316 mF/cm2 (at 2 mA/cm2). The capacitance retention rate and conductivity rate maintain over 90 % after undergoing 100 bends.The maximum energy density and cycling stability are characterized to be 83.6 μWh/cm2 and up to 96 % retention after 10,000 cycles. These results significantly outperform those previously reported for paper-based counterparts. Overall, our work presents a facile and versatile strategy for assembling high-loading, paper-based flexible supercapacitors network architecture that can be employed in developing large-scale energy storage devices.

User-Centric Access Network (UCAN) for 6G: Motivation, Concept, Challenges and Key Technologies

A universal and flexible network architecture is required to meet the demands for optimal user experience and all coverage types including wide area coverage and ultra-dense coverage in 6G. In this paper, a powerful network architecture, the user-centric access network (UCAN), is proposed to meet the multi-dimensional demands of 6G. After analyzing the motivations and requirements, we introduce the concept, architecture, and networking scenarios of UCAN. UCAN has four distinct features including deeply customized network, elastic reconfigurable network, open and compatible network, and intelligent adaptive network for user services. In deployment, flexible cell can be constructed and updated for a user with the suitable surrounding access points. The challenges and corresponding key technologies to achieve UCAN are then illustrated to include user-centric access and connection management, dynamic AP management, unified management of interference and resource, and lightweight security. Then a simulation result is given to verify the effectiveness of UCAN. Finally, future works are discussed to indicate the research directions for academia and industry.

A Review on Software‐Defined Networking for Internet of Things Inclusive of Distributed Computing, Blockchain, and Mobile Network Technology: Basics, Trends, Challenges, and Future Research Potentials

Internet of things (IoT) and software‐defined networking (SDN) are two relatively recent developments in the field of communication technology that have emerged in response to the growing demand for more efficient, flexible, and dynamic network architectures. As both of these concepts are new, they have received increasing attention from academic or industrial sources to emphasize their potential for integration. This study is aimed at reviewing the literature on SDN for IoT (SDN‐IoT) published from 2014 to 2022 and presenting insights and directions for future research, with a particular focus on cloud, fog, and edge computing. The study collects data from Science Direct, IEEE Explore, and Google Scholar and objectively selects 126 papers and conducts metadata analysis. The study articulates the challenges of managing and orchestrating IoT systems and how SDN can be used to address these challenges by enabling dynamic and flexible network configurations. It delineates not only the function of blockchain (BC) technology in securing and managing IoT networks but also how SDN can be utilized to incorporate BC‐based solutions. Additionally, the potential of SDN for mobile networks is explored, which are increasingly being used to support IoT devices. Finally, this study outlines the issues, challenges, and potential future research directions that may present opportunities for the researchers working in this field, underscoring the demand for more in‐depth investigation and advancement.

IoT Applications, Platforms, Systems, And Framework based on Blockchain

The Internet of Things (IoT) has lately evolved as a new technology capable of providing real-time and cutting-edge sensing capabilities to numerous industries such as healthcare, agriculture, smart cities, smart homes, and supply chain. Because of this technology's inherent promise, it has already seen exponential growth in a wide range of use-cases across numerous application domains. As academics around the world continue to examine its capabilities, there is widespread consensus that in order to get the most out of this technology and fully realise its potential, IoT must be built on a flexible network architecture with strong support for security, privacy, and trust. Blockchain (BC) technology, on the other hand, has lately emerged as a breakthrough technology with the promise to give several beneficial qualities such as robustness, support for integrity, anonymity, decentralisation, and autonomous control. Several BC systems are offered, which may be appropriate for various use-cases, including IoT applications. As a result, the integration of IoT with BC technology is seen as a potential solution to some critical concerns. To do this, a good grasp of the requirements of various IoT applications and the viability of a BC platform for a specific application satisfying its underlying requirements is required. This project explains many ways such as the gateway process and sensor device. By addressing the present blockchain concerns, IoT may enable a variety of security services, all of which are described in detail. Various authors present some common facts on the use of blockchain in IoT, which aids in a thorough understanding of the concept. Blockchain improves security and privacy in IoT platforms. In this project, an extra immutable ledger is created using all of the resources and information mentioned in the existing procedure. [1].

Software defined internet of things in smart city: a review

The concept of smart cities has gained traction to enhance citizens’ quality of life amidst rapid urbanization. Integration of the Internet of Things (IoT) is a key component that allows for gathering real-time data to inform decision-making and drive innovation in urban planning and management. However, managing the amount of data generated and the IoT devices rapid growth poses a challenge that leads to network management, interoperability, security, and scalability issues in smart cities. To overcome such problems, integrating Software Define Networking (SDN) in IoT provides a flexible, scalable, and efficient network architecture that can better support the unique demands of IoT devices and applications. Motivated by the extensive research efforts in the Software Defined Internet of Things (SDIoT), this paper aims to review SDIoT implementation in smart cities. It first introduces the underlying technology along with various practical applications of SDIoT. The comprehension of SDIoT in smart cities focus on IoT application requirements, including interoperability, scalability, low latency requirement, handling of big data, security, and privacy, energy consumption, Quality of Service (QoS), and task offloading. The paper concludes by discussing the future research directions that need to be examined in greater depth.

Optimized flexible network architecture creation against 5G communication-based IoT using information-centric wireless computing

Optimized flexible network architecture creation against 5G communication-based IoT using information-centric wireless computing

Deep partial least squares for instrumental variable regression

AbstractIn this paper, we propose deep partial least squares for the estimation of high‐dimensional nonlinear instrumental variable regression. As a precursor to a flexible deep neural network architecture, our methodology uses partial least squares for dimension reduction and feature selection from the set of instruments and covariates. A central theoretical result, due to Brillinger (2012) Selected Works of Daving Brillinger. 589‐606, shows that the feature selection provided by partial least squares is consistent and the weights are estimated up to a proportionality constant. We illustrate our methodology with synthetic datasets with a sparse and correlated network structure and draw applications to the effect of childbearing on the mother's labor supply based on classic data of Chernozhukov et al. Ann Rev Econ. (2015b):649–688. The results on synthetic data as well as applications show that the deep partial least squares method significantly outperforms other related methods. Finally, we conclude with directions for future research.

Auditory perception architecture with spiking neural network and implementation on FPGA

Spike-based perception brings up a new research idea in the field of neuromorphic engineering. A high-performance biologically inspired flexible spiking neural network (SNN) architecture provides a novel method for the exploration of perception mechanisms and the development of neuromorphic computing systems . In this article, we present a biological-inspired spike-based SNN perception digital system that can realize robust perception. The system employs a fully paralleled pipeline scheme to improve the performance and accelerate the processing of feature extraction. An auditory perception system prototype is realized on ten Intel Cyclone field-programmable gate arrays, which can reach the maximum frequency of 107.28 MHz and the maximum throughput of 5364 Mbps. Our design also achieves the power of 5. 148 W/system and energy efficiency of 845.85 μJ. Our auditory perception implementation is also proved to have superior robustness compared with other SNN systems. We use TIMIT digit speech in noise in accuracy testing. Result shows that it achieves up to 85.75% speech recognition accuracy under obvious noise conditions (signal-to-noise ratio of 20 dB) and maintain small accuracy attenuation with the decline of the signal-to-noise ratio. The overall performance of our proposed system outperforms the state-of-the-art perception system on SNN.

A robust‐link controller placement model for large‐scale software defined networks

AbstractThe software defined network (SDN) is a novel flexible network architecture. For the purpose of facilitating management, multiple controllers need to be placed in large‐scale SDN. When a link failure occurs, the path can be re‐planned by the control layer. However, unreasonable controller placement scheme brings about a sharp latency increase between controllers and switches. The reliability of the SDN is therefore affected. To this end, we define a link robust distance (LRD) by considering the states during link failures and non‐link failures. Then, we use it design a robust link controller placement model (RLCPM) which can reduce the impact of link failures on the delay between the controller and the switch. In addition, we design a heuristic algorithm with low‐time complexity to solve the RLCPM more effectively. Experimental results show that, compared with other models, RLCPM simplifies the controller placement problem when considering a link failure. The maximum latency between controllers and switches of the obtained controller placement scheme is lower.

Empirical Efficiency Modeling of Online + Offline Teaching Evaluation Mode of Courses Based on 6G Real-Time Image Transmission Architecture

Putting forward the requirements of the 6G-oriented space-earth integrated information network architecture, and put forward a flexible and reconfigurable space-earth integrated information network architecture on this basis. On the basis of the research, it puts forward the countermeasures and suggestions to improve the evaluation mode of college English online teaching. From the aspects of curriculum structure, curriculum implementation, evaluation feedback, teacher team construction and talent training, the innovative teaching mode of "online micro-course" integrated into mathematical modeling courses is studied. A set of experimental teaching plans based on small modeling projects and corresponding teaching methods are proposed. The system of learning evaluation, and the effect of curriculum reform was analyzed through empirical teaching.

SEMG-Based Minimally Supervised Regression Using Soft-DTW Neural Networks for Robot Hand Grasping Control

One of the major challenges in robotics consists in developing successful control strategies for robotic grasping devices. In this scenario, one of the most interesting approaches regards the exploitation of surface electromyography(sEMG). In this work, we propose a novel sEMG-based <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">minimally supervised</i> regression approach capable of performing nonlinear fitting without the necessity for point-by-point training data labelling. The proposed method exploits a differentiable version of the Dynamic Time Warping (DTW) similarity – referred to as soft-DTW divergence – as loss function for a flexible neural network architecture. This is a different paradigm with respect to state-of-the-art approaches in which sEMG-based control of robot hands is mainly realized using supervised or unsupervised machine learning based regression. An experimental session was carried out involving 10 healthy subjects in an offline experiment for systematic and statistical evaluations, and an online experiment for the evaluation of the control of a robot hand. The reported results demonstrate that the proposed soft-DTW neural network can be trained by means of a labelling that does not require to be temporally aligned with the sEMG training dataset, while reporting performances comparable with a standard mean square error(MSE)-based neural network. Also, the subjects were able to successfully control a robot hand for grasping motions and tasks with error levels comparable to state-of-the-art regression approaches.