Network Algorithm Research Articles

Data-driven two-dimensional stationary quantum droplets and wave propagations in the amended Gross–Pitaevskii equation with two potentials via deep neural networks learning

In this paper, we develop a systematic deep learning approach to solve two-dimensional stationary quantum droplets (QDs) and investigate their wave propagation in the two-dimensional amended Gross–Pitaevskii equation with Lee–Huang–Yang correction and two kinds of potentials. Firstly, we use the initial-value iterative neural network algorithm for two-dimensional stationary QDs of stationary equations. Then, the learned stationary QDs are used as the initial value conditions for physics-informed neural networks to explore their evolutions in the space-time region. Especially, we consider two types of potentials, one is the two-dimensional quadruple-well Gaussian potential and the other is the P T -symmetric harmonic-oscillator (HO)-Gaussian potential, which lead to spontaneous symmetry breaking and the generation of multi-component QDs. The used deep learning method can also be applied to study wave propagations of other nonlinear physical models.

Joint Physics and Data Driven Geometrical Factors of Array Laterolog in Layered Formations

Numerical geometrical factors (GFs) are developed for array laterolog measurements in one-dimensional (1D) cylindrically and planarly layered formations. The kernel of GFs assumes that laterolog responses can be expressed in terms of linear superposition of formation resistivities at different units. Two techniques, namely physics-driven modeling and data-driven approximation, have been employed to ensure both computational accuracy and efficiency of GFs. Physics-driven modeling utilizes a three-dimensional finite element algorithm to generate high-precision and fully labeled GFs data and library. Subsequently, these predetermined data are trained offline using classical neural network algorithm to establish an implicit relationship between formation parameters and GFs. The joint physics and data-driven GFs presents three main advantages. Firstly, it enables the direct representation of the spatial sensitivity of layered formations both laterally and horizontally in vertical and horizontal wells. Secondly, GFs can be used to rapidly calculate the array laterolog responses. The computation speed can be enhanced by thousands of times in comparison with traditional physic-driven modeling, allowing for real-time data processing. Another noteworthy aspect is that GFs forward modeling can handle formations with arbitrary layers, thereby resolving the fixed-layer modeling issue inherent in traditional data-driven methods. Thirdly, the GFs can be employed to approximate the derivative of logging response with respect to formation resistivity, significantly reducing the complexity of Jacobian matrix calculation for deterministic inversion. These numerical GFs not only serve as an excellent alternative simulator for array laterolog, but also will be helpful to accelerate the modeling and inversion of other logging measurement in layered structures.

PTTS: Zero-knowledge proof-based private token transfer system on Ethereum blockchain and its network flow based balance range privacy attack analysis

Blockchains are decentralized and immutable databases that are shared among the nodes of the network. Although blockchains have attracted a great scale of attention in the recent years by disrupting the traditional financial systems, the transaction privacy is still a challenging issue that needs to be addressed and analysed. We propose a Private Token Transfer System (PTTS) for the Ethereum public blockchain in the first part of this paper. For the proposed framework, zero-knowledge based protocol has been designed using Zokrates and integrated into our private token smart contract. With the help of web user interface designed, the end users can interact with the smart contract without any third-party setup. In the second part of the paper, we provide security and privacy analysis including the replay attack and the balance range privacy attack which has been modeled as a network flow problem. It is shown that in case some balance ranges are deliberately leaked out to particular organizations or adversarial entities, it is possible to extract meaningful information about the user balances by employing minimum cost flow network algorithms that have polynomial complexity. The experimental study reports the Ethereum gas consumption and proof generation times for the proposed framework. It also reports network solution times and goodness rates for a subset of addresses under the balance range privacy attack with respect to number of addresses, number of transactions and ratio of leaked transfer transaction amounts.

Predicting Mortality Risk in Neonatal Patients with AKI with an Artificial Neural Network Algorithm

Predicting Mortality Risk in Neonatal Patients with AKI with an Artificial Neural Network Algorithm

A fault tolerant node placement algorithm for WSNs and IoT networks

The operation of Internet of Things (IoT) Network and Wireless Sensor Networks (WSNs) can be often disrupted by a number of factors, such as node faults, security attacks, as well as path disconnections. Despite any disruptions or any failures of network components the functionality and performance of the network should remain unaltered. An approach that can assist in resolving the above issues is the use of mobile nodes. In this work, we present a Fault Tolerant Node Placement Algorithm (FTNPA) that utilizes mobile nodes for addressing failures in the network. We initially propose a Mobile Fault Tolerant (MobileFT) Framework, that supplies the two main functionalities of the Fault Tolerant Node Placement Algorithm (FTNPA), which are the detection and the recovery. Then, we present two variations of the FTNPA algorithm, the Decentralized FTNPA and the Centralized FTNPA. The first variation uses a decentralized detection method, where the detection is performed by the neighboring nodes in the network, as well as a local recovery method, where a mobile node is placed in a certain position to assist the affected area. Whereas, the second variation employs a centralized detection method, where the sink is responsible for the detection, and a recovery method that creates alternatives paths of mobile nodes towards a destination node. Simulation results show that the proposed algorithms can significantly contribute to the detection and recovery of faults in IoT Networks and WSNs.

A RMSCA algorithm for space division multiplexing elastic optical networks with core switching

Space division multiplexing elastic optical networks (SDM-EONs) have attracted much attention due to the advantages of high capacity, flexibility, and spectrum utilization. Space division multiplexing technology enhances the capacity of a single fiber link by using multi-core fiber (MCF). With the support of MCFs, SDM-EONs will become an important form of future optical transmission networks.In order to reduce the blocking rate of the network, this paper proposes a routing, modulation format, spectrum and core allocation (RMSCA) algorithm based on the maximum number of available cores with core switching. The algorithm selects the spectrum block with the most available cores in the entire path for spectrum allocation by using core switching. We perform simulations on two networks, NSF-Net and UBN24, and compare them with the spectrum allocation algorithm with core switching (FF-ISC-RMSCA), which uses first-time adaptation, and the spectrum allocation algorithm with maximum number of cores available (N-ISC-RMSCA), which does not perform core switching. Simulation results show that the proposed algorithm significantly reduces the bandwidth blocking rate and has high spectrum utilization.

High-risk nuclide screening and parameter sensitivity analysis based on numerical simulation and machine learning

During nuclear accidents, large quantities of radionuclides will be released into the environment, posing serious health hazards to local residents. The screening of high-risk nuclides is critical for the development of subsequent nuclear emergency response measures. In order to overcome the shortcomings of traditional screening methods, a machine learning method was proposed to screen high-risk nuclides and predict their contamination to groundwater more effectively. The performances of Support Vector Machine (SVM), Random Forest (RF) and Back Propagation Neural Network (BPNN) algorithms were compared, and sensitivity analyses of the initial leakage concentration ratio (C0/Cp), distribution coefficient (Kd) and decay coefficient (λ) on the model outputs were performed. Results showed that RF classification model achieved the highest prediction accuracy for screening high-risk nuclides. The contribution of the input parameters ranked as Kd > λ > C0/Cp. BPNN regression model was found to be the best for predicting when high-risk nuclides would pollute groundwater. The output was negatively correlated with C0/Cp and positively correlated with Kd and λ, with the parameter influence ranking as Kd > C0/Cp > λ. The contribution of Kd mainly came from itself, and the contribution of C0/Cp and λ mainly due to their interaction with other parameters.

Direct implementation of AI-Based Facial Recognition for ITSI students

The development of artificial intelligence (AI)-based facial recognition technology has become a significant research topic in the field of computing and security. At the Indonesian Palm Oil Institute (ITSI), AI-based facial recognition is introduced to students to improve their skills in developing AI-based applications. This study aims to implement and test a facial recognition system using a Python program by utilizing a dataset generated independently. This research method involves several stages, namely collecting ITSI students' facial data, data processing, creating a facial recognition model using a machine learning algorithm, and evaluating model performance. The dataset used was developed through a live shooting session involving active student participation. The facial recognition model was trained using a convolutional neural network (CNN) algorithm that was optimized to improve accuracy. The results of the study showed that the developed model was able to achieve high facial recognition accuracy, with an average accuracy rate of 92%. The discussion includes an analysis of factors that affect accuracy, such as variations in lighting and shooting angles, as well as the potential use of this technology in a campus environment, including for attendance and security purposes. The conclusion of this study shows that the implementation of AI-based facial recognition can be effectively applied in an academic environment, as well as providing students with practical experience in developing and testing AI applications. This study also opens up opportunities for further research on improving the performance of facial recognition systems and their application in various real-world scenarios.

Short-term load forecasting by GRU neural network and DDPG algorithm for adaptive optimization of hyperparameters

Short-term load forecasting (STLF) is critical to optimizing power system operation. Deep learning (DL) methods can provide extremely high accuracy for STLF. However, most models in existing research lack adaptive optimization capabilities in the prediction process and suffer from performance degradation. To resolve the above difficulties, we propose a hybrid model (DDPG-GRU) based on gated recurrent units and deep deterministic policy gradients for STLF. First, the GRU network has the advantage of processing multiple time series inputs and can simultaneously consider multi-dimensional load characteristics, thereby making the model more efficient. Since the GRU model structure is relatively complex, choosing a good set of hyperparameters is very difficult. Therefore, the purpose of using DDPG is to optimize the hyperparameters of the GRU model adaptively. The proposed model is a combination of DL methods and reinforcement learning. In order to prove the superiority of the proposed model, it is applied to the load data of Area 1 in China to perform single-step and multi-step load forecasting, respectively. The results show that DDPG-GRU has a better fitting effect than the baseline method. Taking the multi-step prediction results as an example, compared with the classic GRU network, the MAPE, MAE, and RMSE of the proposed model are reduced by 22.75 %, 14.44 %, and 14.02 %, respectively, while the R2 coefficient is increased by 13.23 %. At the same time, we use the China Area 2 data set to verify the universality of the proposed model. Furthermore, we compared the proposed method with state-of-the-art methods and achieved better accuracy.

Email Spam Detection Using a Hybrid Approach of Feedforward Neural Network and Penguin Optimization Algorithm

The electronic communication of today is beset by unwanted junk messages. These are not just a nuisance; they waste our time and energy and clog up our inboxes, which are supposed to be, in many ways, our digital front doors. But how do we keep them from coming? Well, as today's article makes clear, the situation is hardly straightforward. There are various methods that can be used, both traditional and modern, and each has its own set of pros and cons. One method, however, stands out in today's article as one that we think might work well in practice, the good old-fashioned neural network. The method's novelty derives from its use of neural networks, a type of machine learning, in conjunction with the POA. The POA is a powerful optimization algorithm that can perform very well when fine-tuning the weights and biases of a neural network. We therefore used the POA to optimize these two crucial components of our model and achieved a surprising level of accuracy—98.7%. This figure surpasses the next nearest competitor by 2% and demonstrates the efficacy of our method in spam detection while also highlighting the POA's potential in this field. The overall proposed method pushes the spam-detection field forward, but it also demonstrates something even broader: the power of hybrid approaches in machine learning. Neural networks are great—but you have to train them properly, and the use of a particle swarm for that purpose is a neat idea. But in the end, a hybrid spam filter is still a spam filter, and this one does what it's supposed to do better than many rivaling methods.

Surplus value quantification of overdue medical devices based on Kohonen network algorithm.

With the continuous updating and progress of medical equipment, the overdue medical device has problems such as management difficulties, resource waste, and potential security risks. Therefore, this paper used the Kohonen network algorithm to quantitatively evaluate and analyze the surplus value of overdue medical devices. In this paper, the Kohonen network algorithm was used to build a quantitative model of the surplus value of the overdue medical device, and the self-organization characteristics and data-driven learning ability of the Kohonen network were used to predict the surplus value of the equipment more accurately. Support vector machine was used to quantitatively evaluate and predict the surplus value of overdue medical devices, and further optimize the model performance, to provide more accurate and reliable decision support for medical equipment management. The Kohonen network algorithm used in this paper evaluated the correlation between the service life and maintenance cost of eight types of overdue medical devices and quantitatively predicted the surplus value of overdue medical devices with the random forest algorithm. According to the comparison of prediction bias, the maximum deviation between the expected surplus value and the actual surplus value is only 1, and the deviation value by the random forest algorithm is as low as 6, the Kohonen network algorithm in this paper has better prediction performance than the random forest algorithm. In the experiment of comparative analysis and verification by introducing the decision tree algorithm, the average error rate of the Kohonen network algorithm in this paper was only 20.57%, which was far lower than 46.34% of the random forest algorithm and 65.31% of decision tree algorithm. The Kohonen network algorithm used in this paper can effectively quantitatively evaluate and predict the surplus value of overdue medical devices, thus improving the efficiency of medical equipment management, reducing costs, and ensuring patient safety.

Multi-AUV Kinematic Task Assignment Based on Self-Organizing Map Neural Network and Dubins Path Generator.

To deal with the task assignment problem of multi-AUV systems under kinematic constraints, which means steering capability constraints for underactuated AUVs or other vehicles likely, an improved task assignment algorithm is proposed combining the Dubins Path algorithm with improved SOM neural network algorithm. At first, the aimed tasks are assigned to the AUVs by the improved SOM neural network method based on workload balance and neighborhood function. When there exists kinematic constraints or obstacles which may cause failure of trajectory planning, task re-assignment will be implemented by changing the weights of SOM neurals, until the AUVs can have paths to reach all the targets. Then, the Dubins paths are generated in several limited cases. The AUV's yaw angle is limited, which results in new assignments to the targets. Computation flow is designed so that the algorithm in MATLAB and Python can realize the path planning to multiple targets. Finally, simulation results prove that the proposed algorithm can effectively accomplish the task assignment task for a multi-AUV system.

Neurosurrealism in the Service of Revolution: Aesthetic Features and Critical Potential of Neural Network Art

The rapid development of neural network technologies in recent years has given rise to the formation of many interdisciplinary research areas, including neural network aesthetics. The aesthetics of generative creativity today is studied not only in the context of the history of digital art, but also in comparison with the practices of other artistic trends and schools. Thus, the expression “neural surrealism”, which has become entrenched in popular discourse, undoubtedly refers to the aesthetics of classical surrealism, framed and fixed in Andre Breton’s program texts: neural network algorithms allow you to create images that seem both realistic and absurd due to unexpected combinations of objects, distorted proportions and presence of uncanny images. Although “neural surrealism” can be seen as a depoliticized and unbiased game of generated images in contrast to the surrealism of the 1920s and 30s, which was not merely an artistic movement but a radical social project, it appears that the very ability of neural networks to generate extraordinary and unpredictable images holds a certain critical potential. Using the methods of formal-stylistic and ideological-content analysis, the author of the article concludes that “neurosurrealism” in a sense continues the line of classical surrealism to undermine the automatism of perception and patterns of thinking. Generative algorithms become a kind of “exclusion production machines” that allow you to see reality from an unexpected angle. In addition, the very fact of using neural networks in art raises important questions about the nature of creativity, the limits of artificial intelligence and the future of man in the world of smart machines. Neurosurrealism problematizes well-established ideas about the originality and intentionality of artistic expression, which indicates the close connection of generative artistic practices with the aesthetics of classical surrealist creativity. The conducted research will be useful to specialists of a wide profile: media theorists, art historians, philosophers, cultural scientists, as well as developers and representatives of the creative industries.

РОЗРОБКА АДАПТИВНИХ АЛГОРИТМІВ РОЄВОГО ІНТЕЛЕКТУ У ПРОЕКТУВАННІ ТА УПРАВЛІННІ ІНЖЕНЕРНИМИ СИСТЕМАМИ

The article examines the design and management of engineering systems in the context of growing data volumes in local computer networks. With the development of swarm intelligence, the probability of the existence of the necessary information for managing engineering systems increases, but the possibility of finding it decreases. This creates the need to develop new methods and tools for using adaptive algorithms of swarm intelligence. The purpose of such algorithms is to ensure the ability to process information and find queries with maximum relevance, generating the largest number of search results (SERPs) containing technical information. The development of swarm intelligence algorithms is impossible without their intellectualization, which includes semantic and syntactic analysis of texts, natural language tools, and intelligent algorithms for determining the significance of information resources. In digital information retrieval systems (DIRS), a query is formed in the form of keywords or their combinations, connected by logical operations. To search for the same information, different keywords are used, the choice of which is subjective. The first stage of the algorithm consists in determining the set of meaningful correspondences and forming the initial set of requests within the engineering system. To ensure the completeness of the selection, the total relevance of the SERP in relation to the group of significance criteria is considered. There is a need to develop an efficient neural network algorithm to solve the problem of assigning one SERP to each group of query criteria. This will make it possible to distribute SERPs by criteria groups so that each page is evaluated mainly by one criteria group, and the total relevance of all groups is maximized. Thus, the article emphasizes the importance of developing new methods and tools for implementing adaptive swarm intelligence algorithms in engineering systems. Special attention is paid to the development of effective neural network algorithms that will ensure optimal distribution of the relevance of search pages, which will increase the accuracy and efficiency of information search in complex engineering systems.

Software data objects application integrity modeling in medication dispensing errors predictions using machine learning algorithms in workflow-based pharmacy software systems

The study focuses on using the software objects created at each stage of the workflow-based systems (and in our article we can focus on the pharmacy-based medication dispensing software systems) to predict the anomalies or potential issues in that software object constructed at each stage of the workflow using the historical issues recorded in that specific workflow stage using linear regression, decision trees, and neural network algorithms. By utilizing historical data and integrity metrics, the research aims to forecast potential failures and maintain the reliability of software applications. The focus is on employing algorithms such as linear regression, decision trees, and neural networks to enhance predictive accuracy and facilitate informed decisions or recommendations to the workflow users (pharmacists) about the potential medication dispensing error the software objects constructed at that state or workflow could cause and advise to take necessary corrections.

Long-term Evaluation of Machine Learning Based Methods for Air Emission Monitoring.

Machine learning (ML) techniques have been researched and used in various environmental monitoring applications. Few studies have reported the long-term evaluation of such applications. Discussions regarding the risks and regulatory frameworks of ML applications in environmental monitoring have been rare. We monitored the performance of six predictive models developed using ML and statistical methods for 28 months. The six models used to predict NOx emissions were developed using six different algorithms. The model developed with a moderate complexity algorithm, adaptive boosting, had the best performance in long-term monitoring, with a root mean square error (RMSE) of 0.48 kg/hr in the 28-month monitoring period, and passed two of the three relative accuracy test audits. High complexity models based on gradient boosting and neural network algorithms had the best training performance, with a minimum RMSE of 0.23 kg/hr and 0.26 kg/hr, but also had the worst RMSE scores, of 0.51 kg/hr and 0.57 kg/hr, during the monitoring period. In addition, all six models failed all three relative accuracy test audits. The following problems were observed: (1) Complex ML models tended to have overfitting problems, thus indicating the importance of the trade-off between model accuracy and complexity. (2) Model input sensor drift or out of high-frequency ranges from the training data resulted in inaccurate predictions or an accuracy lower than the minimum allowed by regulators. (3) Existing regulatory frameworks must be modernized to keep pace with current machine learning practices. Some statistical tests are unsuitable for applications developed by using ML methods.

Robust joint multiple resources allocation algorithm for cooperative underwater acoustic communication networks

AbstractIn this article, a joint relay selection, power control and time allocation problem is studied to maximize the energy efficiency for the cooperative underwater acoustic communication networks. The joint optimization problem is full of challenges due to the strong coupling of multiple resources and the uncertain characteristics of the underwater acoustic communication scenario. To address this issue, the worst‐case method is employed to transform an original uncertain problem into a deterministic problem. Furthermore, we propose the block coordinate descent‐based method to decouple the strongly coupling multi‐resource allocation problem into three relatively independent sub‐problems. The coupling of multiple resources is completely decoupled, thereby greatly reducing the solving difficulty. In addition, given that the sub‐problems with the fractional objective function are still non‐convex and hard to solve, the Dinkelbach‐based method is proposed to transform the fractional objective function into a subtractive form. At last, the relay selection sub‐problem is transformed into a integer programming problem, and the time allocation sub‐problem is transformed into a linear programming problem, whose optimal solutions can be obtained by some well‐established solution methods. The power allocation problem is transformed into a convex optimization problem, which can be solved by the Lagrangian dual method. Finally, in the proposed iteration structure, the three sub‐problems are alternatingly solved until convergence. Simulation results are presented to demonstrate the efficiency and robustness of the proposed algorithm.

Optimization of Sentiment Analysis for Amikom One Application Reviews Using SMOTE with Artificial Neural Network Algorithm

Optimization of Sentiment Analysis for Amikom One Application Reviews Using SMOTE with Artificial Neural Network Algorithm

Optimal directed acyclic graph federated learning model for energy-efficient IoT communication networks

Federated learning (FL) stimulates distributed on-device computation systems to process an optimum technique efficiency by communicating local process upgrades and global method distribution from aggregation averaging procedure. On-device FL is a standard application in wireless environments, with several mobile devices participating as nodes in the FL network. Managing extensive multi-dimensional process upgrades and resource-constrained computations in large-scale heterogeneous IoT cellular networks can be challenging. This article introduces a Lifetime Maximization using Optimal Directed Acyclic Graph Federated Learning in IoT Communication Networks (LM-ODAGFL) technique. The proposed LM-ODAGFL technique utilizes FL and metaheuristic optimization algorithms for energy-effective IoT networks. The Direct Acyclic Graph (DAG) model addresses device asynchrony in FL while minimizing additional resource usage. The Archimedes Optimization Algorithm (AOA) is designed to optimize the DAG model by reducing both user energy consumption and the training loss of the FL model. The performance validation of the LM-ODAGFL technique is performed by utilizing a series of experimentations. The obtained results of the LM-ODAGFL model demonstrate superior performance by consuming significantly less energy than SDAGFL and ESDAGFL, with values ranging from 0.373 to 0.485 kJ per round on the FMNIST-Clustered dataset and 16.27 to 20.34 kJ per round on the Poets dataset, compared to 0.000 to 1.442 kJ and 0.00 to 63.89 kJ respectively.

A Resource Allocation Algorithm for Cloud-Network Collaborative Satellite Networks with Differentiated QoS Requirements

With the continuous advancement of cloud computing and satellite communication technology, the cloud-network-integrated satellite network has emerged as a novel network architecture. This architecture harnesses the benefits of cloud computing and satellite communication to achieve global coverage, high reliability, and flexible information services. However, as business types and user demands grow, addressing differentiated Quality of Service (QoS) requirements has become a crucial challenge for cloud-network-integrated satellite networks. Effective resource allocation algorithms are essential to meet these differentiated QoS requirements. Currently, research on resource allocation algorithms for differentiated QoS requirements in cloud-network-integrated satellite networks is still in its early stages. While some research results have been achieved, there persist issues such as high algorithm complexity, limited practicality, and a lack of effective evaluation and adjustment mechanisms. The first part of this study examines the state of research on network virtual mapping methods that are currently in use. A reinforcement-learning-based virtual network mapping approach that considers quality of service is then suggested. This algorithm aims to improve user QoS and request acceptance ratio by introducing QoS satisfaction parameters. With the same computational complexity, QoS is significantly improved. Additionally, there has been a noticeable improvement in the request acceptance ratio and resource utilization efficiency. The proposed algorithm solves existing challenges and takes a step towards more practical and efficient resource allocation in cloud-network-integrated satellite networks. Experiments have proven the practicality of the proposed virtual network embedding algorithm of Satellite Network (SN-VNE) based on Reinforcement Learning (RL) in meeting QoS and improving utilization of limited heterogeneous resources. We contrast the performance of the SN-VNE algorithm with DDRL-VNE, CDRL, and DSCD-VNE. Our algorithm improve the acceptance ratio of VNEs, long-term average revenue and delay by an average of 7.9%, 15.87%, and 63.21%, respectively.