Network Capabilities Research Articles

PyBibX – a Python library for bibliometric and scientometric analysis powered with artificial intelligence tools

PurposeThis paper presents pyBibX, a Python library devised to conduct comprehensive bibliometric and scientometric analyses on raw data files sourced from Scopus, Web of Science and PubMed, seamlessly integrating state-of-the-art artificial intelligence (AI) capabilities into its core functionality.Design/methodology/approachThe library executes a comprehensive exploratory data analysis (EDA), presenting outcomes via visually appealing graphical illustrations. Network capabilities have been deftly integrated, encompassing citation, collaboration and similarity analysis. Furthermore, the library incorporates AI capabilities, including embedding vectors, topic modeling, text summarization and other general natural language processing tasks, employing models such as sentence-BERT, BerTopic, BERT, chatGPT and PEGASUS.FindingsAs a demonstration, we have analyzed 184 documents associated with “multiple-criteria decision analysis” published between 1984 and 2023. The EDA emphasized a growing fascination with decision-making and fuzzy logic methodologies. Next, network analysis further accentuated the significance of central authors and intra-continental collaboration, identifying Canada and China as crucial collaboration hubs. Finally, AI analysis distinguished two primary topics and chatGPT’s preeminence in text summarization. It also proved to be an indispensable instrument for interpreting results, as our library enables researchers to pose inquiries to chatGPT regarding bibliometric outcomes. Even so, data homogeneity remains a daunting challenge due to database inconsistencies.Originality/valuePyBibX is the first application integrating cutting-edge AI capabilities for analyzing scientific publications, enabling researchers to examine and interpret these outcomes more effectively. pyBibX is freely available at https://bit.ly/442wD5z.

QuanFormer: A Transformer-Based Precise Peak Detection and Quantification Tool in LC-MS-Based Metabolomics.

In metabolomic analysis based on liquid chromatography coupled with mass spectrometry, detecting and quantifying intricate objects is a massive job. Current peak picking methods still cause high rates of incorrectly picked peaks to influence the reliability and reproducibility of results. To address these challenges, we developed QuanFormer, a deep learning method based on object detection designed to accurately quantify peak signals. Our algorithm combines the feature extraction capabilities of convolutional neural networks (CNNs) with the global computation capability of Transformer architecture. Data training in QuanFormer by using nearly 20,000 annotated regions-of-interest (ROIs) ensures unique prediction via bipartite matching, achieving 96.5% of the average precision value on the test set. Even without retraining, QuanFormer achieves over 90% accuracy in distinguishing true from false peaks. Performance was further analyzed using visualization techniques applied to the encoder and decoder layers. We also demonstrated that QuanFormer could correct retention time shifts for peak alignment and generally surpass the existing methods, including MZmine 3 and PeakDetective, to obtain a larger number of picked peaks and higher accurate quantification. Finally, we also carried out metabolomic analysis in a clinical cohort of breast cancer patients and utilized QuanFormer to detect and quantify the potential biomarkers. QuanFormer is open-source and available at https://github.com/LinShuhaiLAB/QuanFormer.

Reinforcement Learning Decision-Making for Autonomous Vehicles Based on Semantic Segmentation

In the complex and stochastic traffic flow, ensuring safe driving requires improvements in perception and decision-making. This paper proposed a decision-control method that leveraged the scene perception and understanding capabilities of semantic segmentation networks and the stable convergence strategies of Deep Reinforcement Learning (DRL) algorithms to achieve more accurate and effective autonomous driving decision-control. Perception features obtained from cameras and sensors equipped with a semantic segmentation model were used as input for the intelligent agent. DRL algorithms were employed to update decisions based on reward feedback. Experimental results on the CARLA simulation platform demonstrated that the semantic segmentation network effectively identified obstacles, vehicles, and drivable areas, providing high-quality perception data input for the intelligent agent’s decision-making model. Compared to the original algorithms, the proposed Double Deep Q-Network-Semantic Segmentation (DDQN-SS) and Proximal Policy Optimization-Semantic Segmentation (PPO-SS) increased the reward value by approximately 25% and enhanced driving stability by 14.2% and 28.5%, respectively, enabling more stable and precise decision-control during driving. The method proposed in this paper has better improved the decision-control performance of PPO and DDQN in complex scenarios.

Scalable superconductor neuron with ternary synaptic connections for ultra-fast SNN hardware

Abstract A novel high-fan-in differential superconductor neuron structure designed for ultra-high-performance Spiking Neural Network (SNN) accelerators is presented. Utilizing a high-fan-in neuron structure allows us to design SNN accelerators with more synaptic connections, enhancing the overall network capabilities. The proposed neuron design is based on superconductor electronics fabric, incorporating multiple superconducting loops, each with two Josephson Junctions. This arrangement enables each input data branch to have positive and negative inductive coupling, supporting excitatory and inhibitory synaptic data. Compatibility with synaptic devices and thresholding operation is achieved using a single flux quantum (SFQ) pulse-based logic style. The neuron design, along with ternary synaptic connections, forms the foundation for a superconductor-based SNN inference. To demonstrate the capabilities of our design, we train the SNN using snnTorch, augmenting the PyTorch framework. After pruning, the demonstrated SNN inference achieves an impressive 96.1% accuracy on MNIST images. Notably, the network exhibits a remarkable throughput of 8.92 GHz while consuming only 1.5 nJ per inference, including the energy consumption associated with cooling to 4K. These results underscore the potential of superconductor electronics in developing high-performance and ultra-energy-efficient neural network accelerator architectures.

Planning model of a low-carbon landscape garden environment based on PSO-BP

Abstract A particle swarm optimization-back propagation neural network (PSO-BP) is proposed. First, we collect and preprocess the planning data for low-carbon landscape environment to ensure accuracy and consistency of data; then we propose the PSO-BP model that combines the global optimization characteristics of particle swarm algorithm and the nonlinear mapping capability of the backpropagation neural network. Empirical studies show that this model can effectively reduce energy consumption and carbon emissions, thus improving the ecological environment quality, improve the ecological service function, and effectively promote the sustainable development of low-carbon landscape buildings.

GrapHisto: A Robust Representation of Graph-Structured Data for Graph Convolutional Networks

Machine learning from graphs is an established branch of AI research motivated by the relevance of applications that involve graph-structured data. The most popular instance is the graph neural network (GNN). On the other hand, due to the promising results of deep learning models in the most diverse fields of application, several efforts have been made to replicate these successes when dealing with graphical data. A prominent specimen of the kind is the graph convolutional network (GCN). Along these lines, the paper propose a novel approach for processing graphs that exploits the capabilities of convolutional neural networks (CNNs) to learn from images. This is achieved by means of a new representation of graphs, called GrapHisto, that portrays graphs in the form of characteristic “pictures”. The GrapHisto is in the form of graph-specific, unique tensors encapsulating the graph topology and its features (i.e., the labels associated with vertexes and edges). This representation is fed to a CNN, and the resulting machine is termed GrapHisto-CNN. The paper provides some theoretical investigations of the properties of the approach, and proposes solutions to some practical issues. An experimental evaluation of the GrapHisto-CNN is reported, revolving around two setups: classification of synthetically-generated graphs, and molecule classification form the dataset QM9. The results show that the approach is effective and robust, and that it compares favorably with GNNs and GCNs.

Optimal Configuration Strategy of Soft Open Point in Flexible Distribution Network Considering Reactive Power Sources

The intelligent soft open point (SOP) has powerful power flow regulation capabilities in the distribution network. If applied to the distribution network, it can flexibly cope with the output uncertainty of unmanageable distributed energy sources. However, considering the investment, operation, and maintenance costs, as well as the assistance of reactive power equipment, the site selection and capacity determination of SOP have become an urgent problem to be solved. This article proposes the optimal configuration strategy of SOP in a flexible interconnected distribution network, taking into account the features of distributed generation and reactive power sources. Firstly, based on the unpredictability of DG output, this paper uses improved sensitivity analysis to determine the optimal SOP installation location. Subsequently, with the optimization objective of minimizing the annual cost of the distribution network, this paper considers the characteristics of DGs, CBs, and OLCTs and uses second-order cone programming to optimize and solve SOP capacity under constraints such as trends. Finally, in the enhanced IEEE 33-node distribution system model, the effects of different scenarios on node voltage, reactive power components, and SOP location and capacity are compared.

An Intelligent Electric Vehicle Charging System in a Smart Grid Using Artificial Intelligence

ABSTRACTThe rapid combination of the electric vehicles into the recent transportation prefers very efficient charging systems involved in grid conditions. This increasing adoption of electric vehicles demands a dynamic and intelligent framework to control charging, confirming optimal grid performance, load balancing, and cost efficiency. In this work, we developed an optimized deep learning framework using the combined structure of Whale‐Optimized Neuro‐Fuzzy Classification for controlling electric vehicle charging within the grid. The increasing involvement of electric vehicle's produces new difficulties, involving overload of grid, and energy management, in real‐time and optimized decision making process. The Whale‐Optimized Neuro‐Fuzzy Classification method uses the hybrid abilities of neuro‐fuzzy systems, integrates the capability of the neural networks and also optimize using a Whale Optimization Algorithm for improved accuracy and efficiency. This proposed method maintains the charging and discharging process of electric vehicles, which have several factors like grid load, priorities of the vehicle and preferences of the user. The neuro‐fuzzy system combines deep convolutional neural network and fuzzy logic to predict charging patterns, considering user preferences, grid demand, renewable energy availability, and so on. This method contribute to the enhancement of energy systems, denotes the future requirement of future smart cities. Evaluation metrics included power usage, energy loss, cost, and processing speed. Analysis of experimental results revealed the accuracy of 99% for the proposed method compared to existing techniques.

Research on leakage and diffusion behavior of hydrogen doped natural gas in integrated pipeline corridors based on data drive

With the wide application of hydrogen-doped natural gas (HBNG) in end users, laying pipelines in urban, comprehensive pipe corridors has become increasingly common. However, the leakage and diffusion of hydrogen-doped natural gas in confined or semi-confined spaces (e.g., utility corridors) can pose a severe safety hazard, as methane and hydrogen gas mixtures have a higher risk of explosion. Therefore, studying hydrogen-doped natural gas’s leakage and diffusion behavior in the comprehensive pipe gallery is essential to ensure its safe operation. This paper establishes a numerical model to study the diffusion law of hydrogen-doped natural gas leakage, and the concentration distribution under different conditions is analyzed. The evolution of the leakage and diffusion of hydrogen-doped natural gas under different hydrogen doping ratios, wind speeds, inlet and outlet spacing, and leakage port sizes were simulated, and the effects of these factors on gas diffusion and explosion hazard volume were discussed. In addition, the backpropagation neural network (BPNN) combined with the global optimization capability of genetic algorithm and the nonlinear mapping capability of neural network is used in this paper to provide a reliable technical means for the accurate prediction of explosion risk volume, which has important application value in the safety design of pipeline corridor and accident prevention and control. The results show that the diffusion range of gas in the pipe corridor increases significantly with the increase of hydrogen mixing ratio. When the hydrogen mixing ratio decreases from 20% to 0, the explosion volume of CH4 decreases by 12.25%. The explosion volume of H2 is close to 0. At the same time, the greater the distance between inlet and outlet, the wider the spread of the dangerous area, when the distance between inlet and outlet is reduced from 200 m to 100 m, the explosion volume of CH4 is reduced by 99.92%, and the explosion volume of H2 is reduced by 100%. In the case of emergency, the reasonable design of Distance between inlet and outlet and air flow configuration can help to quickly discharge harmful gases, ensure the safe evacuation and equipment maintenance in the pipe corridor, and have guiding significance for the ventilation design of the pipe corridor.

Alchemical Free-Energy Calculations at Quantum-Chemical Precision.

In the past decade, machine-learned potentials (MLP) have demonstrated the capability to predict various QM properties learned from a set of reference QM calculations. Accordingly, hybrid QM/MM simulations can be accelerated by replacement of expensive QM calculations with efficient MLP energy predictions. At the same time, alchemical free-energy perturbations (FEP) remain unachievable at the QM level of theory. In this work, we extend the capabilities of the Buffer Region Neural Network (BuRNN) QM/MM scheme toward FEP. BuRNN introduces a buffer region that experiences full electronic polarization by the QM region to minimize artifacts at the QM/MM interface. An MLP is used to predict the energies for the QM region and its interactions with the buffer region. Furthermore, BuRNN allows us to implement FEP directly into the MLP Hamiltonian. Here, we describe the alchemical change from methanol to methane in water at the MLP/MM level as a proof of concept.

Implementation and Testing of V2I Communication Strategies for Emergency Vehicle Priority and Pedestrian Safety in Urban Environments.

This paper explores the development and testing of two Internet of Things (IoT) applications designed to leverage Vehicle-to-Infrastructure (V2I) communication for managing intelligent intersections. The first scenario focuses on enabling the rapid and safe passage of emergency vehicles through intersections by notifying approaching drivers via a mobile application. The second scenario enhances pedestrian safety by alerting drivers, through the same application, about the presence of pedestrians detected at crosswalks by a traffic sensor equipped with neural network capabilities. Both scenarios were tested at two distinct intelligent intersections in Lioni, Avellino, Italy, and demonstrated notable effectiveness. Results show a significant reduction in emergency vehicle response times and a measurable increase in driver awareness of pedestrians at crossings. The findings underscore the potential of V2I technologies to improve traffic flow, reduce risks for vulnerable road users, and contribute to the advancement of safer and smarter urban transportation systems.

Programmable packet-optical network security and monitoring using DPUs with embedded GPUs [Invited

Data processing units (DPUs) with embedded graphics processing units (GPUs) have the potential to revolutionize optical network functionalities at the edge. These advanced units can significantly enhance the performance and capabilities of optical networks by integrating powerful processing capabilities directly at the network edge, where data is generated and consumed. We explore the use cases for DPUs in optical data monitoring with local artificial intelligence (AI) processing and embedded security. This paradigm shift aims to enable more efficient data handling, reduced latency, and improved overall network performance by leveraging local AI processing capabilities embedded within DPUs. In this paper, we show how DPUs can analyze vast amounts of optical data in real-time, implementing advanced data analysis algorithms and security protocols directly on the DPUs to provide robust monitoring and protection for the optical networks. Results indicate that DPUs with embedded GPUs can significantly improve the detection and response times to network anomalies, performance issues, and security threats.

Analysis and Research on the Intelligent Control System of Comprehensive Traffic Signals

The existing urban traffic signal control system exhibits certain inefficiencies, including prolonged waiting times and frequent traffic congestion. Research indicates that the integration of neural networks can enhance the effectiveness of intelligent traffic control systems, potentially improving overall traffic flow and reducing delays. Neural network is a highly parallel, nonlinear and highly redundant system. Meanwhile, the self-learning and self-organizing capabilities of neural network have unique advantages for those systems that cannot establish accurate mathematical models. According to the characteristics of complex, variable and random traffic conditions at urban intersections, this paper analyzes the traffic signal control by using neural network control method. This paper introduces a design method of intelligent traffic light based on dynamic time adjustment of traffic flow. By detecting the traffic flow on site, and then allocating the green time of each lane according to the neural network algorithm, the traffic flow dynamic adjustment can be realized, and the traffic capacity of the intersection can be effectively improved. This kind of intelligent control traffic lights can effectively control traffic, and has obvious effects on dreading traffic flow, improving road capacity and reducing traffic accidents.

Deep-learning-assisted identification of sub-diffraction nanodomains in LiNbO3 crystals.

LiNbO3 domain structures have been widely applied in nonlinear beam shaping, quantum light generation, and nonvolatile ferroelectric memory. The recent developments in nanoscale domain engineering techniques make it possible to fabricate sub-diffracted nanodomains in LiNbO3 crystal for high-speed modulation and high-capacity storage. However, it still lacks a feasible and efficient way to characterize these nanoscale domains. In this work, we propose and experimentally demonstrate a deep-learning-assisted identification of sub-diffraction LiNbO3 nanodomain lines. In the experiment, we record the second-harmonic (SH) images of nanodomain lines by using a confocal microscope. The domain linewidths range from 200 nm to 600 nm, which are beyond the spatial resolution of the used microscope (∼800 nm). After training a neural network with 1568 SH images, it is capable of recognizing different nanodomain lines at an accuracy of 81.25%. Our approach leverages the exceptional recognition capability of the neural network, which provides an efficient method to identify sub-diffraction nanodomains from diffraction-limited images.

The improved BW model are optimized based on MLP neural network

<sec>The nuclear mass model has significant applications in nuclear physics, astrophysics, and nuclear engineering. The accurately predictions of binding energy are crucial for research on nuclear structure, reactions, and decay. However, traditional mass models exhibit large errors in double magic number regions and heavy nuclei regions. These models struggle to effectively describe shell effects and parity effects in nuclear structures, and also fail to capture the subtle differences observed in experimental results.</sec><sec>This study shows the strong modeling capabilities of MLP neural networks, which optimizes the parameters of the nuclear mass model, and reduces prediction errors in key regions and globally. The neural network takes the features as neutron number, proton number, and binding energy, and the labels as mass-model coefficients. The training set is the multiple sets of calculated nuclear mass model coefficients. Through extensive experimentation, the optimal parameters are determined to ensure model convergence speed and stability. The Adam optimizer is employed to adjust the weights and biases of the network, for reducing the mean squared error loss during training.</sec><sec>The trained neural network model with minimal loss was used to predict the optimal coefficients of the nuclear mass model based on the AME2020 dataset. The optimized BW2 model significantly reduces root-mean-square errors in double magic number and heavy nuclei regions. Specifically, the optimized model achieved reductions of approximately 28%, 12%, and 18% in root-mean-square errors near Z(N) = 50, Z(N) = 50 (82), and Z(N) = 82 (126), respectively. In heavy nuclei regions, the errors were reduced by 48%. The BW3 model, incorporating higher-order symmetry energy terms, reduced global root-mean-square errors from 1.86 MeV to 1.63 MeV after parameter optimization using the neural network.</sec><sec>This work reveals that the model with newly optimized coefficients not only exhibits significant error reductions near double magic numbers but also shows improvements in binding energy predictions for both neutron-rich and neutron-deficient nuclei. Furthermore, the model demonstrates good improvements in describing parity effects, accurately capturing parity-related differences in isotopic chains with varying proton numbers.</sec><sec>This study demonstrates the tremendous potential of MLP neural networks in optimizing nuclear mass model parameters and provides a novel method for optimizing parameters in more complex nuclear mass models. Moreover, the proposed method applies to nuclear mass models with implicit or nonlinear relationships, offering new perspectives for further development of nuclear mass models.</sec>

Cross-layer latency analysis for 5G NR in V2X communications.

The 5G network was developed to push the capabilities of wireless networks to previously unseen performance limits, e.g., transmission rates of several gigabits per second, latency of less than a millisecond, and millions of devices connected at the same time. To meet these requirements, it is necessary to access new spectrum (the so-called millimeter waves) and use techniques such as Massive MIMO (Multiple-Input Multiple-Output) and beamforming. This required the design of a new radio interface, known as 5G NR, that includes improvements to its physical components and new protocols. The performance of the 5G network will depend heavily on the behavior of these new protocols under certain configuration parameters, traffic conditions, device density, and network architecture. This paper introduces an analytical model for the performance evaluation of 5G NR. The developed model describes the behavior of the different layer 1 and 2 protocols involved in 5G radio communication. Using the model, it is possible to evaluate the performance of 5G NR in terms of throughput and latency, two key performance metrics used to describe QoS (Quality of Service) thresholds of different applications. The protocol layer approach gives the model sufficient granularity to identify critical behaviors that significantly impact performance. This can help focus efforts on improving these key points or propose improvements/modifications to the operation of network protocols or devices. The use of this model for performance evaluation is exemplified by studying a Remote Driving scenario operated over 5G. This scenario has very stringent delay requirements, which, according to the model's results, can be satisfied if the network conditions are adequate. This model and its results can be used as a starting point for performance evaluations of application involving end-to-end (E2E) communications.

Augmenting a spine CT scans dataset using VAEs, GANs, and transfer learning for improved detection of vertebral compression fractures

In recent years, deep learning has become a popular tool to analyze and classify medical images. However, challenges such as limited data availability, high labeling costs, and privacy concerns remain significant obstacles. As such, generative models have been extensively explored as a solution to generate new images and overcome the stated challenges. In this paper, we augment a dataset of chest CT scans for Vertebral Compression Fractures (VCFs) collected from the American University of Beirut Medical Center (AUBMC), specifically targeting the detection of incidental fractures that are often overlooked in routine chest CTs, as these scans are not typically focused on spinal analysis. Our goal is to enhance AI systems to enable automated early detection of such incidental fractures, addressing a critical healthcare gap and leading to improved patient outcomes by catching fractures that might otherwise go undiagnosed. We first generate a synthetic dataset based on the segmented CTSpine1K dataset to simulate real grayscale data that aligns with our specific scenario. Then, we use this generated data to evaluate the generative capabilities of Deep Convolutional Generative Adverserial Networks (DCGANs), variational autoencoders (VAEs), and VAE-GAN models. The VAE-GAN model demonstrated the highest performance, achieving a Fréchet Inception Distance (FID) five times lower than the other architectures. To adapt this model to real-image scenarios, we perform transfer learning on the GAN, training it with the real dataset collected from AUBMC and generating additional samples. Finally, we train a CNN using augmented datasets that include both real and generated synthetic data and compare its performance to training on real data alone. We then evaluate the model exclusively on a test set composed of real images to assess the effect of the generated data on real-world performance. We find that training on augmented datasets significantly improves the classification accuracy on a test set composed of real images by 16 %, increasing it from 73 % to 89 %. This improvement demonstrates that the generated data is of high quality and enhances the model's ability to perform well against unseen, real data.

Unleashing R&D networks for ambidexterity: The interplay between internal and external networking capabilities

Unleashing R&D networks for ambidexterity: The interplay between internal and external networking capabilities

Developing of neural network computing methods for solving inverse elasticity problems

This paper examines the use of neural network methods to solve inverse problems in the mechanics of elastic materials. The aim is to design physics-informed neural networks that can predict the parameters of structural components, and the physical properties of materials based on a specified displacement distribution. A key feature of the specified neural networks is the integration of differential equations and boundary conditions into the loss function calculation. This approach ensures that the error in approximating unknown functions has a direct impact on optimizing the network's weights. As a result, the resulting neural network approximations of unknown functions comply with the differential equations and boundary conditions. To test the capabilities of the designed neural networks, inverse problems involving the bending of plates and beams have been solved, focusing on determining one or two unknown parameters. Comparison of predicted and exact values demonstrates high accuracy of the constructed neural network models, with a relative prediction error of less than 3 % across all cases. Unlike analytical methods for solving inverse problems, the primary advantage of physics-informed neural networks is their flexibility when addressing both linear and nonlinear problems. For instance, the same network architecture can be employed to solve various boundary-value problems without modification. Compared to classical numerical methods, the parallelization capability of neural networks is inherently supported by modern software libraries. Therefore, the application of physics-informed neural networks for solving inverse elasticity problems of plates and beams is effective, as evidenced by the achieved relative errors and the computational robustness of the method. In practice, the proposed solution can be used for relevant calculations during the design of structural elements. The developed software code can also be integrated into automated design systems or computer algebra systems

The analysis of urban collaborative governance in public health emergencies with fuzzy theory based on BP algorithm

This study seeks to improve urban supply chain management and collaborative governance in the context of public health emergencies (PHEs) by integrating fuzzy theory with the Back Propagation Neural Network (BPNN) algorithm. By combining these two approaches, an early warning mechanism for supply chain risks during PHEs is developed. The study employs Matlab software to simulate supply chain risks, incorporating fuzzy inference techniques with the adaptive data modeling capabilities of neural networks for both training and testing. The results demonstrate that the proposed model effectively identifies factors contributing to supply chain deterioration, with a warning error as low as 0.001, significantly enhancing the accuracy and timeliness of demand forecasting. The BPNN algorithm, through its self-learning and adaptive features, facilitates dynamic optimization and precise scheduling across various stages of the supply chain. This capability is particularly valuable in addressing challenges associated with sudden demand spikes and resource allocation. As a result, the mechanism is able to accurately and promptly identify adverse trends in the supply chain, thereby enhancing the efficiency and flexibility of urban emergency responses, mitigating risks, and offering both theoretical and practical contributions to urban collaborative governance.