Network Configuration Research Articles

Comparative Analysis of Transit-Oriented Development (TOD) Types in the Metropolitan Region Along the Middle Reaches of the Yangtze River

Currently, with the acceleration of urbanization, traditional transportation modes are increasingly causing congestion, pollution, and resource waste, drawing widespread attention to Transit-Oriented Development (TOD). TOD is an urban development concept that advocates the implementation of high-density, mixed-use land utilization around transit stations to encourage the use of public transportation, reduce reliance on private vehicles, and achieve more sustainable urban growth. The ‘node–place’ model is a classic analytical framework in TOD typology, forming the foundation for assessing TOD effectiveness. However, this model requires expansion due to its limited adaptability. This study aims to bridge this gap by proposing an innovative, network-based ‘node–place–convenience (NPC)’ model to enhance insights on the overall assessment of metro networks. Using a combination of CRITIC weighting and K-means++ clustering, this study evaluates TOD in cities with metros in the middle reaches of the Yangtze River. By assessing node, place, and convenience values of metro stations, this study compares how different urban structures, population distributions, and metro network configurations impact travel behavior, economic vitality, and regional sustainability. The results show that TOD degree in Wuhan decreases from urban to suburban areas, presenting ‘center to sub-center’ pattern in Changsha, and presenting ‘ring-radial’ distribution across the city center in Nanchang. The clustering results divide TOD benefits into six groups, with Changsha performing the best, followed by Wuhan, while Nanchang still has room for improvement. The average TOD benefits for Wuhan, Changsha, and Nanchang are 0.28, 0.35, and 0.28.

A Detailed Inspection of Machine Learning Based Intrusion Detection Systems for Software Defined Networks

The growing use of the Internet of Things (IoT) across a vast number of sectors in our daily life noticeably exposes IoT internet-connected devices, which generate, share, and store sensitive data, to a wide range of cyber threats. Software Defined Networks (SDNs) can play a significant role in enhancing the security of IoT networks against any potential attacks. The goal of the SDN approach to network administration is to enhance network performance and monitoring. This is achieved by allowing more dynamic and programmatically efficient network configuration; hence, simplifying networks through centralized management and control. There are many difficulties for manufacturers to manage the risks associated with evolving technology as the technology itself introduces a variety of vulnerabilities and dangers. Therefore, Intrusion Detection Systems (IDSs) are an essential component for keeping tabs on suspicious behaviors. While IDSs can be implemented with more simplicity due to the centralized view of an SDN, the effectiveness of modern detection methods, which are mainly based on machine learning (ML) or deep learning (DL), is dependent on the quality of the data used in their modeling. Anomaly-based detection systems employed in SDNs have a hard time getting started due to the lack of publicly available data, especially on the data layer. The large majority of existing literature relies on data from conventional networks. This study aims to generate multiple types of Distributed Denial of Service (DDoS) and Denial of Service (DoS) attacks over the data plane (Southbound) portion of an SDN implementation. The cutting-edge virtualization technology is used to simulate a real-world environment of Docker Orchestration as a distributed system. The collected dataset contains examples of both benign and suspicious forms of attacks on the data plane of an SDN infrastructure. We also conduct an experimental evaluation of our collected dataset with well-known machine learning-based techniques and statistical measures to prove their usefulness. Both resources we build in this work (the dataset we create and the baseline models we train on it) can be useful for researchers and practitioners working on improving the security of IoT networks by using SDN technologies.

Employing Evolutionary Computing and Hybrid Artificial Neural Networks to Improve Drug Discovery

An ultimate relevant translational scientific endeavour that contributes to human vulnerability and happiness might be the creation and advancement of medications. Fast drug discovery procedures necessitate using contemporary computational approaches to tackle pharma data's complexities and high complexity. By combining Evolutionary Computing with Hybrid Artificial Neural Networks (EC-HANNs), this research introduces a novel strategy for optimizing and speeding up the drug development process. To handle various drug-target relations, predict the efficacy of compounds, and discover more accurate potential medications, the proposed model employs EC to evolve the computational construction and hyperparameters of HANNs in real-time. This innovation makes the model a flexible framework. Through repeated refinement of EC- HANN designs, the EC Module uses Particle Swarm Optimization (PSO) to choose the best configuration for individual drug discovery tasks. The model's distinctive feature is that it dynamically adjusts the network configuration to match the details of each drug discovery activity by using PSO to optimize the HANN's architecture and hyperparameters. Regarding sequential biological data, the HANN Module employs Convolutional Neural Networks (CNNs) to glean features for pattern recognition over time. By extracting high-level spatial information from genetic data, CNN can better identify prospective medication candidates. When tested on several benchmark datasets, the proposed framework demonstrates superior performance over traditional neural networks across the board regarding prediction accuracy, convergence speed, and model durability. As a powerful tool, this hybrid approach can simplify drug discovery, leading to more efficient drug development.

The power of social networks and social media’s filter bubble in shaping polarisation: an agent-based model

AbstractTthe role social media platforms play on the emergence of polarisation is an ongoing debate in the political communication literature. Social media’s filter bubbles and online echo chambers shape people’s opinions by curating the information they have available. However, the extent to which this is the case remains unclear. Social simulation scholars have provided valuable insights into the subject through opinion dynamics models and agent-based modelling approaches. This article proposes a social simulation approach to the topic of opinion dynamics from a political communication perspective to understand how social network configurations and the media environment contribute to the emergence of national identity polarisation. We built an agent-based simulation model of national identity dynamics with a multilayer multiplex network of interacting agents in a hybrid media environment of both, traditional media and social media platforms. We use the Catalan secessionist movement to ground, contextualise and empirically inform parts of our model. We found that the initial social network setup conditions had a large impact on the emergence of polarisation amongst agents. In particular, homophily-based social networks composed of a majority of like-minded individuals produced greater polarisation compared to random networks. This was aggravated in the presence of social media filtering algorithms, selectively exposing agents to supportive information. These results emphasise the importance of both the selective exposure by social media filtering algorithms and one’s social networks (echo chambers) for polarisation to emerge. This interaction reinforces the influence of social media platforms and social networks have on the emergence of polarisation.

Networks for healthcare delivery: asystematic literature review.

Network configurations have been proposed as an efficient form of organisation and a promising area of research; however, a lack of conceptual clarity can be noted. The purpose of this review is to allow for a broad appreciation of network configurations and provide guidance for future studies of the concept. A systematic literature review was conducted based on the PRISMA method; Scopus, Web of Science, PubMed and the Cochrane Library were searched for conference proceedings and journal articles describing organisational networks to integrate resources aimed at care delivery. Around 80 articles were included in the final review and analysed thematically and by use of bibliographic coupling. The last decades have seen an increase in the frequency of articles describing networks for healthcare delivery. The most common contexts are care for multiple and/or long-term conditions. Three clusters of articles were found, corresponding to different conceptualisations of networks in healthcare: efficiency-enhancing cooperation, efficiency-enhancing integration and involvement for cocreation. To increase conceptual clarity and allow the research on network configurations in healthcare to produce meta-learnings and guidance to practice, scholars are advised to provide ample descriptions of studied networks and relate them to established network classifications. The current review has only included articles including networks as a key concept, which provides a focused overview of the use of network configurations but limits the insights into similar approaches not described explicitly as networks.

Artificial Neural Network Model to Predict the Exportation of Traditional Products of Colombia

This article develops the design, training, and validation of a computational model to predict the exportation of traditional Colombian products using artificial neural networks. This work aims to obtain a model using a single multilayer neural network. The number of historical input data (delays), the number of layers, and the number of neurons were considered for the neural network design. In this way, an experimental design of 64 configurations of the neural network was performed. The main arduousness addressed in this work is the significant difference (in tons) in the values of the considered products. The results show the effect that occurs due to the different range values, and one of the proposals made allows this limitation to be handled appropriately. In summary, this work seeks to provide essential information for formulating a model for efficient and practical application.

Method for Locating Secondary Circuit Faults in Substations Based on Graph Neural Networks

To improve the accuracy and portability of fault location in secondary circuits of smart substations, a fault location method for secondary circuits based on graph neural networks is proposed. First, a fault analysis of the secondary circuits in smart substations is conducted, and a graph database model of the secondary circuits is constructed, revealing the connection relationships between the secondary devices. Then, the fault location problem in secondary circuits is defined as a graph classification problem, and a fault graph generation model is proposed based on a representation method for fault information in secondary circuits. Finally, a fault location model for secondary circuits based on graph neural networks is constructed, and a performance optimization method based on binary cross-entropy is proposed to achieve accurate fault location in substation secondary circuits. Using the secondary circuits of a 220 kV smart substation as a reference, different case studies of secondary circuit faults are generated by altering the network topology, connection relationships, and network configurations through the fault graph generation model. Experiments comparing the proposed location method with other models show that this method has higher location accuracy and robustness.

Can Transportation Networks Contribute to the Sustainable Development of Urban Agglomeration Spatial Structures?

The advancements in global urbanisation have significantly elevated the configuration of transportation networks for the sustainable development of urban agglomeration spatial structures (UASS). Using a comprehensive panel dataset covering 140 counties and districts in the Chengdu-Chongqing Economic Circle from 2014 to 2023, this study empirically examines the impact of transportation networks on the sustainability of UASS. It elucidates the underlying mechanisms using spatial Durbin, spatial spillover and multiple mediation effect models. The findings reveal that transportation networks considerably enhance the sustainability of UASS and generate substantial positive spatial spillover effects. The decay boundary of the spatial spillover effects exhibits a transition from positive to negative, eventually approaching ineffectiveness. The heterogeneity analysis indicates significant variations in terms of transportation network expansion and regional functional division on the sustainability of UASS across regions with various levels of economic development. This outcome suggests that regional development policies should carefully consider regional economic development disparities. The mechanism analysis further reveals that transportation networks enable the sustainability of UASS by accelerating regional hierarchical systems and regional connectivity.

Abnormal intrinsic brain functional network dynamics in patients with retinal detachment based on graph theory and machine learning

Backgroundand purpose: The investigation of functional plasticity and remodeling of the brain in patients with retinal detachment (RD) has gained increasing attention and validation. However, the precise alterations in the topological configuration of dynamic functional networks are still not fully understood. This study aimed to investigate the topological structure of dynamic brain functional networks in RD patients. MethodsWe recruited 32 patients with RD and 33 healthy controls (HCs) to participate in resting-state fMRI. Employing the sliding time window analysis and K-means clustering method, we sought to identify dynamic functional connectivity (dFC) variability patterns in both groups. The investigation into the topological structure of whole-brain functional networks utilized a graph theoretical approach. Furthermore, we employed machine learning analysis, selecting altered topological properties as classification features to distinguish RD patients from HCs. ResultsAll participants exhibited four distinct states of dynamic functional connectivity. Compared to the healthy control (HC) group, patients with RD experienced a significant reduction in the number of transitions among these four states. Additionally, the dynamic topological properties of RD patients demonstrated notable changes in both global and node-specific characteristics, with these changes correlating with clinical parameters. The support vector machine (SVM) model used for classification achieved an accuracy of 0.938, an area under the curve (AUC) of 0.988, and both sensitivity and specificity of 0.937. ConclusionThe alterations in the topological properties of the brain in RD patients may indicate the integration function and information exchange efficiency of the whole brain network were reduced. In addition, the topological properties hold considerable promise for distinguishing between RD and HCs.

Bifurcation Instability Modulated by a Connecting Channel Leads to Periodic Water Partitioning in a Simple Channel Network

AbstractWater and mass transport in distributary channel networks play an important role in nourishing fluvial and coastal wetlands, and are largely determined by the morphological configurations of channel bifurcations. While the morphological equilibrium of a single channel bifurcation has been extensively studied, the equilibrium configurations of channel networks with connecting channels linking the bifurcating branches, that is, the “bifurcation‐connecting channel” units that are commonly found in rivers, deltas and estuaries, remain elusive. In this simple yet representative channel network of the “bifurcation‐connecting channel” unit, we observed through numerical simulations an oscillatory water partitioning under moderate Shields stress and channel aspect ratio, in addition to the steady‐state solutions reported in previous studies. The oscillatory water partitioning indicates a newly discovered periodic solution, which is an emergent behavior under constant boundary conditions. We found that the periodic solution is primarily due to the dynamic interactions between bifurcation instability and water surface slope advantage in the two branches modulated by the reversable discharges through the connecting channel, under moderate Shields stress and channel aspect ratio. In such cases, the developed slope advantage in the subordinate branch can suppress the deepening of the dominant branch and eventually lead to the shifting of the dominant branch. In contrast, the channel network attains a steady‐state solution when the slope advantage or the bifurcation instability is dominant with relatively low and high Shields stress (or channel aspect ratio). Our results improve the understanding on the evolution and restoration of channel networks under increasing human interventions in global deltas.

Reconfigurable data intensive service for low latency cyber-physical systems and IoT communication

<span>The fourth industrial revolution is realized through the many developments in cyber-physical systems (CPS) made possible by the widespread use of the internet of things (IoT). CPS sensor networks must enable mobile and wireless CPSs with their specific flexibility and heterogeneity needs without compromising quality of service (QoS). The research article focuses on reconfigurable data communication hardware for numerous IoT-supporting infrastructures and performance estimation using delay, power, throughput, and packet delivery ratio (PDR) for different IoT node configurations. Tree topology-based network configuration from cloud data to sensor fog organizers, sensor network directors, and IoT-embedded sensors is supported. Functional simulation is performed in iFoGSim, Xilinx ISE, and Modelsim 10.0 with a maximum of 64 variable nodes programmed for data communication and interplay verification with a minimum delay of 9.1 ns, maximum frequency of 319 MHz, power of 7.5 mW, throughput of 0.280, and maximum PDR=1. The simulation is applicable for fog computing and CPS processed from different alters in specific topologies.</span>

High-temperature heat pumps in industrial heating networks: A study on energy use, emissions, and economics

Industrial heat significantly contributes to global primary energy use and primarily relies on fossil-fuel combustion. Recovering residual heat in the industry offers a means to reduce overall energy use. However, the temperature and amount of residual heat available varies widely across industrial sites. Some may have a large amount of residual heat available at relatively high temperatures, while others may not have any residual heat available. Furthermore, for most industries, the residual heat available is at temperatures below 100 °C, while the heat demands are at higher temperatures. Hence, clustering these industries by industrial heating networks, using high-temperature heat pump integration, could offer a promising solution. Research on this concept regarding energy use, emissions and economics is however lacking in the literature. This study however distinguishes and subsequently compares three different heat network configurations in terms of their energy use, carbon emissions and financial appraisal. These configurations include a ‘consumer based heat upgrading network’, a ‘supplier based heat upgrading network’ and a ‘supplier based heat upgrading network with an additional hot water network’. For this purpose a generic methodology is developed, using first and second law principles completed with empirical data for performance and costs. The methodology is applied to data collected from ten companies clustered within the North Sea Port, Ghent (Belgium). The results indicate that the first configuration exhibits the most efficient use of energy and consequently also has the lowest carbon emissions. In addition it also has the lowest levelized cost of heat. This configuration shows, depending on maximum supply temperature of the heat pump, a potential reduction in carbon emissions ranging from 70 % to 80 % in comparison to natural gas boilers. Considering low gas prices, a positive financial appraisal is difficult without carbon taxation. On the other hand, an evaluation during the energy crisis of 2021–2022 indicates that the even without carbon taxation, the levelized cost of heat decreases by 19 % compared to a gas boiler at a maximum heat pump temperature of 160 °C. It was also found that in scenarios of dynamic energy prices a hybrid configuration of a consumer based heat upgrading network and a natural gas boiler could lower the LCOH compared to the individual solutions, by up to 7.6 % compared to the best individual solution. This is done by activating the technology with the lowest operational cost in each time frame.

A New Deep Learning Methodology for Alarm Supervision in Marine Power Stations.

Marine engineering officers operate and maintain the ship's machinery during normal navigation. Most accidents on board are related to human factors which, at the same time, are associated with the workload of the crew members and the working environment. The number of alarms is so high that, most of the time, instead of helping to prevent accidents, it causes more stress for crew members, which can result in accidents. Convolutional Neural Networks (CNNs) are being employed in the recognition of images, which depends on the quality of the images, the image recognition algorithm, and the very complex configuration of the neural network. This research study aims to develop a user-friendly image recognition tool that may act as a visual sensor of alarms adjusted to the particular needs of the ship operator. To achieve this, a marine engineering simulator was employed to develop an image recognition tool that advises marine engineering officers when they are conducting their maintenance activities, with the aim to reduce their stress as a work risk prevention tool. Results showed adequate accuracy for three-layer Convolutional Neural Networks and balanced data, and the use of external cameras stands out for user-friendly applications.

Reducing Successive Interference Cancellation Iterations in Hybrid Beamforming Multiuser Massive Multiple Input Multiple Output Systems Through Grouping Users with Symmetry Channels

This paper presents a comprehensive exploration of advanced beamforming techniques tailored for millimeter-wave (mm-Wave) communication systems. In response to the burgeoning demand for higher data rates, coupled with the constraints of power consumption and hardware complexity, this study focuses on developing a hybrid beamforming framework optimized for downlink scenarios, specifically targeting groups of users based on the approximate symmetry of their channels. The primary innovation of this research lies in leveraging the symmetry of channels among near users to develop a group-based successive interference cancellation (SIC) algorithm. Unlike traditional approaches that address interference on a per-user basis, this algorithm utilizes channel symmetry within clusters of users to reduce computational complexity and improve the efficiency of SIC. By grouping users with symmetrical channel characteristics, the algorithm simplifies the interference management process while maintaining system performance. The proposed system demonstrates notable advantages over existing non-linear algorithms through extensive simulations and performance evaluations, particularly in terms of spectral efficiency and computational complexity. In this study, we further emphasize the importance of balancing spectral efficiency improvements with reduced computational demands, offering a nuanced trade-off that accommodates various operational requirements. The flexible optimization framework provided showcases the system’s adaptability to diverse deployment scenarios and network configurations.

Adaptive rewiring: a general principle for neural network development.

The nervous system, especially the human brain, is characterized by its highly complex network topology. The neurodevelopment of some of its features has been described in terms of dynamic optimization rules. We discuss the principle of adaptive rewiring, i.e., the dynamic reorganization of a network according to the intensity of internal signal communication as measured by synchronization or diffusion, and its recent generalization for applications in directed networks. These have extended the principle of adaptive rewiring from highly oversimplified networks to more neurally plausible ones. Adaptive rewiring captures all the key features of the complex brain topology: it transforms initially random or regular networks into networks with a modular small-world structure and a rich-club core. This effect is specific in the sense that it can be tailored to computational needs, robust in the sense that it does not depend on a critical regime, and flexible in the sense that parametric variation generates a range of variant network configurations. Extreme variant networks can be associated at macroscopic level with disorders such as schizophrenia, autism, and dyslexia, and suggest a relationship between dyslexia and creativity. Adaptive rewiring cooperates with network growth and interacts constructively with spatial organization principles in the formation of topographically distinct modules and structures such as ganglia and chains. At the mesoscopic level, adaptive rewiring enables the development of functional architectures, such as convergent-divergent units, and sheds light on the early development of divergence and convergence in, for example, the visual system. Finally, we discuss future prospects for the principle of adaptive rewiring.

Predicting Obesity via Deep Learning: The Role of Chrononutrition

Abstract Background Obesity is a significant public health challenge, prompting the need for assessing effective tools for its monitoring and prevention. Chrononutrition investigates the role of timing, regularity and frequency of food intake on body metabolism and health. Here we aim to check if data on the distribution of calorie intake in the day may improve BMI prediction as compared to using only data on total day intake. Methods We apply deep learning on chrononutritional data on calorie intake over 6 daily timeslots from a nationally representative cross-sectional survey sample of the Italian population (INRAN-SCAI 2005/2006) comprising 2313 Italian adults 18-64 ys old with 3 day diet diaries. In particular, we implemented three deep neural network models, varying network configurations and feature selection. The 1st includes 18 (6 for each day diary) chrononutritional variables and the 3 day total intakes, beside age and sex; the 2nd includes age, sex and the 18 chrononutritional variables only; the 3rd uses age, sex and the 3 day totals only. We applied Early Stopping to limit overfitting. Optimization was conducted using the Adam algorithm, minimizing the mean squared error (RMSE), while mean absolute error (MAE) was the primary performance indicator. Results The results highlight that Model 3 outperformed the other models with MAE=2.514 and RMSE=3.476, indicating that for the purpose of predicting obesity, information on the time-of-day distribution of calorie intake is not increasing predictive ability of BMI on top of age, sex and total calorie intake in the day. Conclusions Additional use of day-time intake information worsened prediction of BMI via deep learning using this cross sectional Italian survey. However the error made is still sizeable and warrants the inclusion of other variables; our results don’t rule out the role of chrononutrition on metabolic health which may act through other biological mechanisms related to specific nutrients. Key messages • Chrononutrition data don’t improve BMI prediction over total calorie intake data in a cross-setional representative sample of the Italian population. • Deep learning approach to BMI prediction shows the importance of targeted selection of features in public health nutrition.

Deep learning-based whole-brain B1 +-mapping at 7T.

This study investigates the feasibility of using complex-valued neural networks (NNs) to estimate quantitative transmit magnetic RF field (B1 +) maps from multi-slice localizer scans with different slice orientations in the human head at 7T, aiming to accelerate subject-specific B1 +-calibration using parallel transmission (pTx). Datasets containing channel-wise B1 +-maps and corresponding multi-slice localizers were acquired in axial, sagittal, and coronal orientation in 15 healthy subjects utilizing an eight-channel pTx transceiver head coil. Training included five-fold cross-validation for four network configurations: used transversal, sagittal, coronal data, and was trained on all slice orientations. The resulting maps were compared to B1 +-reference scans using different quality metrics. The proposed network was applied in-vivo at 7T in two unseen test subjects using dynamic kt-point pulses. Predicted B1 +-maps demonstrated a high similarity with measured B1 +-maps across multiple orientations. The estimation matched the reference with a mean relative error in the magnitude of (2.70 ± 2.86)% and mean absolute phase difference of (6.70 ± 1.99)° for transversal, (1.82 ± 0.69)% and (4.25 ± 1.62)° for sagittal ( ), as well as (1.33 ± 0.27)% and (2.66 ± 0.60)° for coronal slices ( ) considering brain tissue. trained on all orientations enables a robust prediction of B1 +-maps across different orientations. Achieving a homogenous excitation over the whole brain for an in-vivo application displayed the approach's feasibility. This study demonstrates the feasibility of utilizing complex-valued NNs to estimate multi-slice B1 +-maps in different slice orientations from localizer scans in the human brain at 7T.

Enhancing hosting capacity for electric vehicles in modern power networks using improved hybrid optimization approaches with environmental sustainability considerations

The increasing adoption of electric vehicles (EVs) presents both opportunities and challenges for power networks. While EVs have the potential to reduce carbon emissions, accommodating their growing power demand requires careful planning to prevent overloading and mitigate environmental impacts. This paper introduces an integrated hosting capacity model to facilitate higher EV penetration while maintaining environmental standards. In addition to EV charging stations, the model incorporates transmission lines, reactive power compensators, energy storage systems, and thyristor-controlled series compensators to ensure a reliable power supply. The model aims to maximize EV charging station deployment, minimize greenhouse gas emissions, and optimize net present value through hosting capacity strategies. Three hosting capacity plans are proposed to analyze the impact of prioritizing one of these objectives over the others in network configurations. Accurate EV demand forecasting is critical for this model, and a swarm intelligence forecasting algorithm is proposed to explore various forecasting approaches. The model is complex and involves nonlinear multi-objective optimization. To solve it, a new hybrid optimization algorithm is introduced, combining the features of the Marine Predators Algorithm and the Honey Badger Algorithm. Three hybridization schemes—Series Hybrid Scheme, Population Division Scheme, and Switching Strategy Scheme—are developed to address the optimization challenges effectively. The results show that the first and second hybridization schemes are the most effective for solving the EV load forecasting models, with a robustness of at least 90%. In contrast, the robustness of the third scheme reaches only 30% in some models. Simulation studies on the IEEE 9-bus network and the IEEE 30-bus system validate the model’s effectiveness in integrating EVs while achieving environmental sustainability objectives. The findings show the superiority of the proposed hybrid schemes in solving the hosting capacity model in terms of finding optimal solutions. However, the third scheme required less computing time than the others, with its convergence time being at least 33.3% shorter.

Microstructure evolution and mechanical behavior of 2024 aluminum alloy under electric pulse treatment

This study examined the effects of electric pulse treatment (EPT) on solution-treated 2024 alloy. We found that the combined effect of non-uniform stress field caused by thermal expansion and localized Joule heating promoted the formation of helical dislocations. During the subsequent aging process, these severely deformed helical dislocations formed a network configuration, which accelerated the coarsening of the S phase, and the S phase also retained a helical shape. Compared to conventional solution-treated samples, the yield strength of the EPT samples increased by 24 % with almost no loss of fracture elongation. The increase in strength is primarily due to the increase of volume fraction of rod-shaped S phase，enhancing the matrix's resistance to deformation. This study proposes a simple and rapid method to adjust dislocation configurations and aging precipitation through electric pulses, offering new insights for the industrial application of aluminum alloys to swiftly enhance mechanical properties.

Design of an intelligent data analysis platform for pharmaceutical forecasts

This study considers the task to design a data analysis platform with predictive capabilities of neural networks. The object of research is intelligent decision-making systems built on deep learning methods. The proposed intelligent platform takes into account the specificity of working with data in the dynamic and uncertain environment of the pharmaceutical market. Its main purpose is the processing of various data formats, such as time series, regression, classification data sets to create forecasts based on various indicators. At the core of the platform architecture, along with technologies for backend and frontend development (HTML, JS, CSS, C#, .NET), MSSQL Server and TSQL for database management, are AI Microservices (Python, Flask); they are responsible for artificial intelligence services, in particular neural networks. In order to identify the optimal model, which is able to effectively solve regression problems based on the selected indicators, the study analyzed several configurations of neural networks on End-to-end machine learning platforms. Distinctive features of the architecture of the designed data analysis platform include its ability to dynamically switch between different machine learning models based on predefined indicators and criteria such as prediction accuracy and model selection. Improved interpretation of forecasts through the use of Explainable AI enables effective decision-making in the pharmaceutical industry. The functioning of the proposed instrumental decision-making base is demonstrated on the examples of forecasting trends in the consumption of pharmaceuticals by different groups in the pharmaceutical markets of different countries. Automating the model selection and prediction loss minimization process in a comprehensive data analysis platform (CDAP) improves forecast accuracy by approximately 15 % compared to traditional manually selected models.