Adaptive Optimization Research Articles

AIGO-DTI: Predicting Drug-Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms.

Artificial intelligence-based methods for predicting drug-target interactions (DTIs) aim to explore reliable drug candidate targets rapidly and cost-effectively to accelerate the drug development process. However, current methods are often limited by the topological regularities of drug molecules, making them difficult to generalize to a broader chemical space. Additionally, the use of similarity to measure DTI network links often introduces noise, leading to false DTI relationships and affecting the prediction accuracy. To address these issues, this study proposes an Adaptive Iterative Graph Optimization (AIGO)-DTI prediction framework. This framework integrates atomic cluster information and enhances molecular features through the design of functional group prompts and graph encoders, optimizing the construction of DTI association networks. Furthermore, the optimization of graph structure is transformed into a node similarity learning problem, utilizing multihead similarity metric functions to iteratively update the network structure to improve the quality of DTI information. Experimental results demonstrate the outstanding performance of AIGO-DTI on multiple public data sets and label reversal data sets. Case studies, molecular docking, and existing research validate its effectiveness and reliability. Overall, the method proposed in this study can construct comprehensive and reliable DTI association network information, providing new graphing and optimization strategies for DTI prediction, which contribute to efficient drug development and reduce target discovery costs.

The capsular polysaccharide obstructs wall teichoic acid functions in Staphylococcus aureus.

The cell envelope of Staphylococcus aureus contains two major secondary cell wall glycopolymers: capsular polysaccharide (CP) and wall teichoic acid (WTA). Both the CP and the WTA are attached to the cell wall and play distinct roles in S. aureus colonization, pathogenesis, and bacterial evasion of host immune defenses. We aimed to investigate whether CP interferes with WTA-mediated properties. Strains with natural heterogeneous expression of CP, strains with homogeneous high CP expression and CP-deficient strains were compared to WTA deficient controls regarding WTA dependent phage binding, cell adhesion, IgG deposition, and virulence in vivo. WTA-mediated phage adsorption, specific antibody deposition and cell adhesion were negatively correlated with CP expression. WTA, but not CP, enhanced the bacterial burden in a mouse abscess model, while CP overexpression resulted in intermediate virulence in vivo. CP protects the bacteria from WTA-dependent opsonization and phage binding. This protection comes at the cost of diminished adhesion to host cells. The highly complex regulation and mostly heterogeneous expression of CP has probably evolved to ensure the survival and optimal physiological adaptation of the bacterial population as a whole.

Simulation-Based Robust and Adaptive Optimization Method for Heteroscedastic Transportation Problems

Simulation-Based Robust and Adaptive Optimization Method for Heteroscedastic Transportation Problems

Intelligent control algorithm for dynamic positioning control system

Introduction: The dynamic positioning system resists the environmental forces such as wind, wave and current acting on the ship through the thruster, so that the ship can remain in the position required by the sea level as much as possible, and the operation is very convenient. But its current dynamic positioning ability can not meet people's needs.Methods: A Kalman filter based on untracked optimization was designed for dynamic positioning control system. Then the intelligent control algorithm is designed for the dynamic positioning top-level controller and thrust optimal distribution controller, which occupy an important position in the system, namely the adaptive weight variation particle swarm optimization algorithm and thrust optimal distribution algorithm.Results and Discussion: The average position error of three degrees of freedom after filter processing is 1.53 m. Compared with other mainstream controllers, the mean root error of controllers based on adaptive weight variation particle swarm optimization in environment A and B is 2.295 and 1.8 m, respectively. In environment C, the controller based on thrust optimization allocation algorithm can get the optimal solution when the full rotary thruster reaches the 7 s and the channel thruster reaches the 4 s. The thrust exclusion zone is crossed at 46 s in environment D. In the dynamic positioning capability curve of the system, the experimental hull can balance the different environmental loads at all angles. In summary, the intelligent control algorithm proposed in this paper can effectively improve the positioning ability of the dynamic positioning control system and meet the needs of people for ship navigation today.

Hybrid Intelligent Control System for Adaptive Microgrid Optimization: Integration of Rule-Based Control and Deep Learning Techniques

Microgrids (MGs) have evolved as critical components of modern energy distribution networks, providing increased dependability, efficiency, and sustainability. Effective control strategies are essential for optimizing MG operation and maintaining stability in the face of changing environmental and load conditions. Traditional rule-based control systems are extensively used due to their interpretability and simplicity. However, these strategies frequently lack the flexibility for complex and changing system dynamics. This paper provides a novel method called hybrid intelligent control for adaptive MG that integrates basic rule-based control and deep learning techniques, including gated recurrent units (GRUs), basic recurrent neural networks (RNNs), and long short-term memory (LSTM). The main target of this hybrid approach is to improve MG management performance by combining the strengths of basic rule-based systems and deep learning techniques. These deep learning techniques readily enhance and adapt control decisions based on historical data and domain-specific rules, leading to increasing system efficiency, stability, and resilience in adaptive MG. Our results show that the proposed method optimizes MG operation, especially under demanding conditions such as variable renewable energy supply and unanticipated load fluctuations. This study investigates special RNN architectures and hyperparameter optimization techniques with the aim of predicting power consumption and generation within the adaptive MG system. Our promising results show the highest-performing models indicating high accuracy and efficiency in power prediction. The finest-performing model accomplishes an R2 value close to 1, representing a strong correlation between predicted and actual power values. Specifically, the best model achieved an R2 value of 0.999809, an MSE of 0.000002, and an MAE of 0.000831.

A back‐to‐back coordination‐based learning scheme for deceiving reactive jammers in distributed networks

AbstractReactive jammers select jamming strategies according to the users’ responses; thus, conventional anti‐jamming methods such as frequency hopping are inadequate to defeat the jamming attack. In this article, the authors propose a novel uncoupled deception scheme to trap the reactive jammer into attacking a decoy channel in distributed networks. Specifically, the authors design a multi‐functional network utility for every user to mislead the jammer with a minimum energy consumption while achieving the highest network throughput. Based on the network utility, the anti‐jamming problem is formulated as an exact potential game such that the existence of Nash equilibrium can be guaranteed theoretically. The authors further propose a back‐to‐back coordination‐based learning algorithm to reach the optimal channel selection and power adaption in a non‐cooperative way. To alleviate the lack of mutual information exchange, the back‐to‐back coordination mechanism derives all users to deceive the jammer by inferring others’ strategies based on a shared belief. Simulation results show that the proposed algorithm yields higher network throughput and efficiency‐cost ratio compared to the state‐of‐the‐art cooperative schemes.

Vibration control by using active electromagnetic shunt damper

It is well-known that the traditional electromagnetic shunt damping (EMSD) techniques are limited by the damping force of electronic components and require a negative resistance (NR) shunt circuit to enhance performance. However, the NR shunt circuit could lead to the EMSD system being unstable. Addressing this, this study proposes an advanced control system that employs active control technology combined with EMSD for vibration control. We first developed a dimensionless mathematical model of the control system, which was then finely tuned using an adaptive simulated annealing particle swarm optimization algorithm. Subsequently, the relationship between control gain and optimal shunt circuit parameters was predicted using a BP neural network. Finally, the proposed Active-EMSD (AEMSD) was experimentally verified. The experimental results demonstrate that the proposed AEMSD not only surpasses traditional thresholds but also excels in isolating low-frequency vibrations. Compared to traditional EMSD, the proposed AEMSD showed improved effectiveness.

Fault Detection and Interactive Multiple Models Optimization Algorithm Based on Factor Graph Navigation System

Accurate and stable positioning is significant for vehicle navigation systems, especially in complex urban environments. However, urban canyons and dynamic interference make vehicle sensors prone to disturbance, leading to vehicle positioning errors and even failures. To address these issues, an adaptive loosely coupled IMU/GNSS/LiDAR integrated navigation system based on factor graph optimization with sensor weight optimization and fault detection is proposed. First, the factor nodes and system framework are constructed based on error models of sensors, and the optimization method principle is derived. Second, the interactive multiple-model algorithm based on factor graph optimization (IMMFGO) is utilized to calculate and adjust sensor weights for global optimization, which will reduce the impact of disturbed sensors. Finally, a multi-stage fault detection, isolation, and recovery (MSFDIR) strategy is implemented based on the IMMFGO results and IMU pre-integration measurements, which can detect significant sensor faults and optimize the system structure. Vehicle experiments show that our IMMFGO method generally obtains better performance in positioning accuracy by 23.7% compared to adaptive factor graph optimization (AFGO) methods, and the MSFDIR strategy possesses the capability of fault sensor detection, which provides an essential reference for multi-source vehicle navigation systems in urban canyons.

Dynamic Regularized Adaptive Cluster Optimization (DRACO) for Quantitative Cardiac Cine MRI in Complex Arrhythmias.

Irregular cardiac motion can render conventional segmented cine MRI nondiagnostic. Clustering has been proposed for cardiac motion binning and may be optimized for complex arrhythmias. To develop an adaptive cluster optimization method for irregular cardiac motion, and to generate the corresponding time-resolved cine images. Prospective. Thirteen with atrial fibrillation, four with premature ventricular contractions, and one patient in sinus rhythm. Free-running balanced steady state free precession (bSSFP) with sorted golden-step, reference real-time sequence. Each subject underwent both the sorted golden-step bSSFP and the reference Cartesian real-time imaging. Golden-step bSSFP images were reconstructed using the dynamic regularized adaptive cluster optimization (DRACO) method and k-means clustering. Image quality (4-point Likert scale), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), edge sharpness, and ventricular function were assessed. Paired t-tests, Friedman test, regression analysis, Fleiss' Kappa, Bland-Altman analysis. Significance level P < 0.05. The DRACO method had the highest percent of images with scores ≥3 (96% for diastolic frame, 93% for systolic frame, and 93% for multiphase cine) and the percentages were significantly higher compared with both the k-means and real-time methods. Image quality scores, SNR, and CNR were significantly different between DRACO vs. k-means and between DRACO vs. real-time. Cardiac function analysis showed no significant differences between DRACO vs. the reference real-time. DRACO with time-resolved reconstruction generated high quality images and has early promise for quantitative cine cardiac MRI in patients with complex arrhythmias including atrial fibrillation. Stage 2.

English letter recognition based on adaptive optimization spiking neural P systems

English letter recognition based on adaptive optimization spiking neural P systems

Multi-objective load balancing based on adaptive osprey optimization algorithm

Multi-objective load balancing based on adaptive osprey optimization algorithm

Accurate calculation of losses in amorphous alloy cores based on a dynamic Jiles-Atheron model under wide frequency and variable temperature operating conditions

The stator core of the high-speed amorphous alloy permanent magnet synchronous motor(HSAAPMSM）experiences significant temperature fluctuations due to exposure to a high-frequency alternating magnetic field. We introduce the dynamic Jiles-Atheron(J-A) model under wide frequency and variable temperature operating conditions to achieve accurate modeling for stator core loss. In contrast to previous modeling techniques, this approach does not rely on amount of experience data and laborious parameter identifications. The adaptive chaotic dung beetle optimization algorithm is applied to improve the effectiveness of parameter identification. The temperature-dependent static J-A model is modified into a dynamic J-A model by combining the field separation approach with the Riemann-Liouville (R-L) fractional derivative theory to enable the model's application under high-frequency operating circumstances. Finally, the model described in this study is verified through experimentation and can be used to precisely calculate the loss of amorphous alloy cores.

Detailed Insight into the Behaviour of Chlorophyll a Fluorescence Transient Curves and Parameters during Different Times of Dark Adaptation in Sunflower Leaves

The reason for this examination is today’s wide usage of chlorophyll a fluorescence (ChlF) among researchers worldwide to measure photosynthetic efficiency. Although the instructions of the ChlF measuring device clearly emphasize the need for methodology adjustments, depending on the specific plant species, many researchers use the usual 30 min of dark adaptation before measurement. Namely, before any ChlF measurement, it is necessary to determine the specific duration of the leaf adaptation to the conditions of darkness of each plant tissue. Because of the numerous uses of the ChlF measurements, we decided to conduct this research to determine whether the appearance of the curves and parameter values depend on the time of sunflower leaf tissue adaptation to dark conditions. Therefore, this research aimed to examine the optimal adaptation time of sunflower tissue to dark conditions to obtain timely precise measurements and credible appearance of ChlF transient curves as well as accurate parameter values. The research was carried out on the sunflower hybrid Luka with 0, 15, 30, 45, 60, 75 and 90 min of dark adaptation in the vegetative, budding and flowering stages in the field conditions. According to the analyzed transient curves and parameters, it was determined that sunflower leaves should be kept in dark conditions for at least 15 min before the measurement of ChlF, which leads to the complete oxidation of PSII and the electron transport chain prior to a saturating pulse of light.

Improved adaptive war strategy optimization algorithm assisted-adaptive multi-head graph attention mechanism network for remaining useful life of complex equipment

The remaining useful life (RUL) of complex equipment is an important criterion to ensure stable operation. In recent years, deep learning-based methods for predicting the RUL of complex equipment have attracted wide attention. However, it is only able to obtain the potential information in the Euclidean space, which hinders their ability to capture the deeply degradation information. Thus, graph neural networks have gradually entered the researchers’ field of vision. Despite the fact that graph neural networks are able to accomplish the task of RUL for complex equipment, there are still limitations that restrict the prediction performance in practical engineering. To address this challenge, an improved adaptive war strategy optimization algorithm assisted-adaptive multi-head graph attention mechanism network (IWSO-LMGAT) is proposed. For one thing, a learnable attention mechanism is proposed to adjust the weights of different heads dynamical and improve the limitation of GAT in obtaining deep degradation information. In addition, since hyperparameters are essential elements affecting the predicted result, inspired by the “no-free lunch” principle, an improved mathematical expression is described to avoid the issue such as precocity, fall into local optimums for WSO so that the optimal hyperparameters of the LMGAT could be obtained. The effectiveness and advancement of IWSO-LMGAT are validated on the CMAPSS dataset, and experimental results show that the proposed method could provide competitive forecasted results compared to traditional methods, that is, R2 = 0.9939, RMSE = 4.3638, and MAPE = 0.0137; this illustrates the IWSO-LMGAT’s potential for the RUL prediction of complex equipment.

Research on small target segmentation method in dual-energy X-ray images of coal and gangue based on APSO-C_Otsu

ABSTRACT Compared with wet coal preparation and traditional dry coal preparation, detection of coal and gangue with small particle size is a difficult problem for dual-energy X-ray separation technology. And small target segmentation is the premise of its detection, which is poor due to the fewer number of pixels and texture information in coal and gangue dual-energy X-ray images. So, the Otsu with crotch structure based on Adaptive Particle Swarm Optimization (APSO) for small target segmentation method is proposed, called after APSO-C_Otsu. Firstly, the Otsu with crotch structure is used to increase the contrast between small target and background. Meanwhile, the APSO algorithm was used to optimize the Otsu algorithm with crotch structure in order to improve its convergence speed and reduce its calculation amount. Finally, after binarization, the location of the targets are labeled based on the bwlabel algorithm. The results revealed that the APSO-C_Otsu algorithm could effectively segment the coal and gangue with a particle size of 5–30 mm, and was also applicable to the coal and gangue with the particle size larger than 30 mm, which was of great significance for accurate detection of coal and gangue and the improvement of coal utilization.

Impact of Dynamic Phytoplankton Stoichiometry on Global Scale Patterns of Nutrient Limitation, Nitrogen Fixation, and Carbon Export

AbstractPhytoplankton stoichiometry modulates the interaction between carbon, nitrogen and phosphorus cycles. Environmentally driven variations in phytoplankton C:N:P can alter biogeochemical cycling compared to expectations under fixed ratios. In fact, the assumption of fixed C:N:P has been linked to Earth System Model (ESM) biases and potential misrepresentation of responses to future change. Here we integrate key elements of the Adaptive Trait Optimization Model (ATOM) for phytoplankton stoichiometry with the Carbon, Ocean Biogeochemistry and Lower Trophics (COBALT) ocean biogeochemical model. Within a series of global ocean‐ice‐ecosystem retrospective simulations, ATOM‐COBALT reproduced observations of phytoplankton N:P, and compared to static ratios, exhibited reduced phytoplankton P‐limitation, enhanced N‐fixation, and increased low‐latitude export, improving consistency with observations and highlighting the biogeochemical implications of dynamic N:P. We applied ATOM‐COBALT to explore the impacts of different physiological mechanisms hypothesized to underlie N:P variation, finding that two mechanisms together drove the observed patterns: proportionality of P‐rich ribosomes in phytoplankton cells to growth rates and reductions in P‐storage during scarcity. A third mechanism which linked temperature with phytoplankton biomass allocations to non‐ribosomal proteins, led only to relatively modest impacts because this mechanism decreased the temperature dependence of phytoplankton growth rates, compensating for changes in N:P. We find that there are quantitative response differences that associate distinctive biogeochemical footprints with each mechanism, which are most apparent in highly productive low‐latitude regions. These results suggest that variable phytoplankton N:P makes phytoplankton productivity and export resilient to environmental changes, and support further research on the physiological and environmental drivers of phytoplankton stoichiometry and biogeochemical role.

Adaptive energy optimization strategy of island renewable power-to-hydrogen system with hybrid electrolyzers structure

Adaptive energy optimization strategy of island renewable power-to-hydrogen system with hybrid electrolyzers structure

Evaluation of the accuracy of seven intraoral scanners for the full dentate and partially edentulous complete-arch mandibular casts: An in vitro comparison

Statement of problemIntraoral scanners (IOSs) are widely used in dentistry, providing high accuracy in short-range scanning. Nevertheless, when scanning the full dental arch, it remains a challenge. Furthermore, there is a lack of studies reporting the differences in scan accuracy between dental arches with large-span mucosal areas and fully dentate casts or optimal IOS selection for different dental statuses. PurposeThis study aimed to evaluate the accuracy and scanning time of different IOSs for full dentate (FD) and partially edentulous (PE) casts with missing teeth in the #34–#44 range and to determine the IOSs with the optimal clinical adaptability and scanning accuracy for different complete-arch casts. Material and methodsReference scans of two complete-arch (FD and PE) casts were obtained using a laboratory scanner (Ceramill Map 600). Subsequently, the same casts were scanned ten times each by seven IOSs (3Shape Trios 3, CS3600, Planmeca Emerald, iTero Element 5D, Medit i500, BAMBOO B1, and Shining Aoralscan 3), and the scanning time was recorded. The test data were superimposed on the reference scans for the selected areas, and three-dimensional deviations between the reference and test casts (trueness), and between test casts (precision) were determined using reverse engineering software (Geomagic Wrap). The dataset was analyzed using a two-factor analysis of variance with post-hoc Bonferroni tests. ResultsTwo-factor analysis of variance revealed significant differences in accuracy and scanning time for different casts (P<0.001) and IOSs (P<0.001). For the FD cast, the i500 (0.35±0.11 mm trueness) and CS3600 (0.23±0.12 mm precision) performed worse than the remaining scanners. For the PE cast, the BAMBOO B1(0.89±0.58 mm trueness; 0.88± 0.48mm precision) performed worse than the remaining scanners. There were no differences in the accuracy of scanning between the Element 5D and Emerald for both cast types. However, the scanning time differed significantly between the different IOSs (P<0.001). Regardless of the cast type, the fastest and slowest scans were performed by the Trios3 and CS3600 scanners respectively. ConclusionsThe accuracy and scanning time differed between the different IOSs and types of complete-arch casts.

Weight Decay With Tailored Adam on Scale-Invariant Weights for Better Generalization.

Weight decay (WD) is a fundamental and practical regularization technique in improving generalization of current deep learning models. However, it is observed that the WD does not work effectively for an adaptive optimization algorithm (such as Adam), as it works for SGD. Specifically, the solution found by Adam with the WD often generalizes unsatisfactorily. Though efforts have been made to mitigate this issue, the reason for such deficiency is still vague. In this article, we first show that when using the Adam optimizer, the weight norm increases very fast along with the training procedure, which is in contrast to SGD where the weight norm increases relatively slower and tends to converge. The fast increase of weight norm is adverse to WD; in consequence, the Adam optimizer will lose efficacy in finding solution that generalizes well. To resolve this problem, we propose to tailor Adam by introducing a regularization term on the adaptive learning rate, such that it is friendly to WD. Meanwhile, we introduce first moment on the WD to further enhance the regularization effect. We show that the proposed method is able to find solution with small norm and generalizes better than SGD. We test the proposed method on general image classification and fine-grained image classification tasks with different networks. Experimental results on all these cases substantiate the effectiveness of the proposed method in help improving the generalization. Specifically, the proposed method improves the test accuracy of Adam by a large margin and even improves the performance of SGD by 0.84% on CIFAR 10 and 1.03 % on CIFAR 100 with ResNet-50. The code of this article is public available at xxx.

Towards Sustainable Production: An Adaptive Intelligent Optimization Genetic Algorithm for Solid Wood Panel Manufacturing

Optimizing production processes to conserve resources and reduce waste has become crucial in pursuing sustainable manufacturing practices. The solid wood panel industry, marked by substantial raw materials and energy consumption, stands at the forefront of addressing this challenge. This research delves into production scheduling and equipment utilization inefficiencies, offering innovative solutions for the solid wood panel processing line aimed at achieving environmental sustainability and operational efficiency. The study is articulated through two main segments: (1) an exhaustive analysis and the development of a simulation system for the solid wood panel processing line, delineating all production elements and operational logic, furnished with a user-friendly simulation interface, and (2) a comprehensive evaluation and enhancement of various scheduling algorithms specific to the Flexible Job-Shop Scheduling Problem (FJSP) encountered in solid wood panel workshops. A significant leap forward is made with the introduction of the Adaptive Intelligent Optimization Genetic Algorithm (AIOGA), an evolved version of the standard Genetic Algorithm (GA) engineered for optimal scheduling within the solid wood panel processing line. AIOGA incorporates advanced features such as encoding strategy, population initialization, objective function setting, selection strategy, crossover operation, and mutation operation, demonstrating the methodological depth of the study. We applied AIOGA in a designed FJSP, and AIOGA substantially reduced the maximum completion time to 90 min. It evidenced an improvement of 39.60% over the conventional GA, enhancing the equilibrium of the equipment workload across the system. This research presents a multifaceted strategy to address the scheduling complications inherent in solid wood panel production and highlights the extensive applicability of adaptive intelligent optimization in diverse industrial settings. This study establishes a new paradigm in manufacturing optimization, underlining the valuable integration of sustainability and efficiency in production methodologies.