Iterative Optimization Research Articles

Deepfake Detection using Integrate-backward-integrate Logic Optimization Algorithm with CNN

The emergence of deepfake technology has spurred the need for robust and adaptive methods to detect manipulated media content. This study explores the integration of the Integrate-backward-integrate (IbI) Logic Optimization Algorithm with Convolutional Neural Networks (CNNs) for enhanced deepfake detection. The proposed approach involves a multi-phase iterative process: the CNN initially trained on a diverse dataset encompassing both real and deepfake images. The CNN serves as the foundation for the IbI-driven optimization. The integration phase employs the trained CNN to forward-integrate images, classifying them as real or deepfake. Subsequently, the IbI Logic Optimization Algorithm engages in the backward phase, utilizing feedback from the CNN's performance to iteratively refine the network's parameters, architecture, and feature extraction capabilities. This iterative optimization process aims to adaptively enhance the CNN's ability to discern subtle nuances between authentic and manipulated visuals. The re-integration phase evaluates the refined CNN's performance through multiple iterations, seeking to iteratively improve deepfake detection accuracy. Validation occurs using separate datasets to prevent overfitting and ensure the model's generalizability. The proposed method aims to enhance the CNN's adaptability to evolving deepfake techniques, addressing the dynamic nature of manipulative media creation. This fusion of IbI Logic Optimization with CNNs presents a promising avenue for bolstering deepfake detection capabilities. However, the effectiveness of this approach relies on dataset quality, network architecture, and the dynamic nature of deepfake generation techniques. Continuous refinement and validation are essential to adapt the model to new challenges posed by advancing deepfake technologies.

An efficient steganography scheme based on wavelet transformation for side-information estimation

Previous studies have specifically demonstrated that incorporating high-quality side-information can notably enhance the steganographic security of JPEG images. To obtain more precise side-information estimates, researchers utilize sophisticated deblocking or denoising filters, which enhance security but require a substantial amount of time. The challenge lies in achieving a significant improvement in security and efficiency. This paper introduces a steganographic network named WTSNet, which leverages wavelet transform for estimating side-information through iterative optimization in both the pixel and wavelet domains. The wavelet domain is purposely designed to capture intricate high-frequency texture details and facilitate precise estimation of the side-information. Furthermore, the embedding cost is adjusted based on the polarity of the estimated rounding error, ensuring both secure and efficient performance. Experimental results demonstrate that the proposed scheme substantially enhances the security of conventional JPEG steganography, which relies on additive distortion. Moreover, it outperforms the state-of-the-art JPEG steganography methods based on estimating side-information while consuming less time.

A Review of Machine Learning Methods in Turbine Cooling Optimization

In the current design work, turbine performance requirements are getting higher and higher, and turbine blade design needs multiple rounds of iterative optimization. Three-dimensional turbine optimization involves multiple parameters, and 3D simulation takes a long time. Machine learning methods can make full use of historically accumulated data to train high-precision data models, which can greatly reduce turbine blade performance evaluation time and improve optimization efficiency. Based on the data model, the advanced intelligent combinatorial optimization technology can effectively reduce the number of iterations, find the better model faster, and improve the optimization calculation efficiency. Based on the different cooling parts of turbine blades and machine learning, this research explores the potential of implementing different machine learning algorithms in the field of turbine cooling design.

Digital twin-driven intelligent operation and maintenance platform for large-scale hydro-steel structures

Large-scale hydro-steel structures (LS-HSS) are pivotal in hydraulic engineering, boasting high lift, expansive apertures, and discharge capacities. Conventional methods of operation and maintenance for LS-HSS require a digital revolution to ensure safety, reliability, and durability. This study introduces a novel approach, harnessing the power of a digital twin (DT) to integrate physical and virtual elements in LS-HSS operation and maintenance seamlessly. A digital twin modeling framework of LS-HSS operation and maintenance is first presented, incorporating five levels of a physical entity, a virtual entity, DT data, services, and connections. Subsequently, a DT-driven intelligent operation and maintenance (DT-IOM) platform is constructed and applied, which features real-time mapping, closed-loop control, dynamic health assessment, and intelligent decision-making. This platform provides a pathway for digitally transforming conventional LS-HSS operation and maintenance and paves the way for a new era of intelligent infrastructure management. The proposed approach has been successfully implemented and validated with multiple engineering projects, including radial gates of reservoir spillways, plain gates of flood discharge orifices, and emergency gates of pumped storage power stations. The impressive results demonstrate a significant anomaly response and processing efficiency improvement of over 60%. Moreover, the platform has substantially reduced field inspection time and equipment failure rate by approximately 50% and 20%, respectively. These tangible benefits further highlight the platform’s functional advantages, including its capability for IoT connection, modeling and integration, virtual-real interaction, 2D/3D visualization, and service expansion. The results demonstrate the unique features in the closed loop of perception, analysis, decision-making, and optimization for DT-IOM, especially for integrating data, models, knowledge, and services in LS-HSS intelligent operation and maintenance.

Engineering of a Baeyer-Villiger monooxygenase to Improve Substrate Scope, Stereoselectivity and Regioselectivity.

Baeyer-Villiger monooxygenases belong to a family of flavin-binding proteins that catalyze the Baeyer-Villiger (BV) oxidation of ketones to produce lactones or esters, which are important intermediates in pharmaceuticals or sustainable materials. Phenylacetone monooxygenase (PAMO) from Thermobifida fusca with moderate thermostability catalyzes the oxidation of aryl ketone substrates, but is limited by high specificity and narrow substrate scope. In the present study, we applied loop optimization by loop swapping followed by focused saturation mutagenesis in order to evolve PAMO mutants capable of catalyzing the regioselective BV oxidation of cyclohexanone and cyclobutanone derivatives with formation of either normal or abnormal esters or lactones. We further modulated PAMO to increase enantioselectivity. Crystal structure studies indicate that rotation occurs in the NADP-binding domain and that the high B-factor region is predominantly distributed in the catalytic pocket residues. Computational analyses further revealed dynamic character in the catalytic pocket and reshaped hydrogen bond interaction networks, which is more favorable for substrate binding. Our study provides useful insights for studying enzyme-substrate adaptations.

A design of interactive review for computer aided diagnosis of pulmonary nodules based on active learning

Automatic detection of pulmonary nodule based on computer tomography (CT) images can significantly improve the diagnosis and treatment of lung cancer. However, there is a lack of effective interactive tools to record the marked results of radiologists in real time and feed them back to the algorithm model for iterative optimization. This paper designed and developed an online interactive review system supporting the assisted diagnosis of lung nodules in CT images. Lung nodules were detected by the preset model and presented to doctors, who marked or corrected the lung nodules detected by the system with their professional knowledge, and then iteratively optimized the AI model with active learning strategy according to the marked results of radiologists to continuously improve the accuracy of the model. The subset 5-9 dataset of the lung nodule analysis 2016(LUNA16) was used for iteration experiments. The precision, F1-score and MioU indexes were steadily improved with the increase of the number of iterations, and the precision increased from 0.213 9 to 0.565 6. The results in this paper show that the system not only uses deep segmentation model to assist radiologists, but also optimizes the model by using radiologists' feedback information to the maximum extent, iteratively improving the accuracy of the model and better assisting radiologists.

Comparative analysis for optimal placement of piezoelectric actuators on smart thin plate

In contemporary smart structures, piezoelectric ceramic (PZT) actuators serve a crucial structural function. To construct a smart thin plate that integrates structural health monitoring (SHM) and active vibration control objectives, many placement methodologies were discussed. In current research, two positioning strategies of the attached PZT actuators are compared. The first strategy is a well-known controllability concept where PZT actuators’ optimum positions are obtained by maximizing the eigenvalues of the controllability Grammian matrix. The second strategy employs the energy concept to strategically position PZT actuators so that the utmost amount of exerted work is accomplished by the actuators. Thus, the optimal performance of actuators to provide energy for mitigating unwanted vibrations is maintained, as is the optimal excitation required for SHM in the designated modes. Kirchoff’s classical laminate plate theory (CLPT) is used to define displacements as well as the normal strains of this coupled electro-mechanical system, and then, using the Ritz solution, the modal eigenvalue problem is solved, and mode shapes are obtained. Consequently, normal strains are transformed into spatially dependent functions used to define both the virtual work and the controllability of the Grammian matrix for the PZT actuators as a function of their locations. Finally, iterative optimization based on a genetic algorithm (GA) is used to find the optimum actuator locations in the desired modes. The best location for the PZT actuator or actuators is explored for two specimen plates with different boundary conditions. The results for the two studied positioning strategies are then compared, showing the superiority of the proposed energy-based strategy. Further, a quantitative variance-based uncertainty analysis reveals a low variance of the output results for the proposed strategy.

Iterative intelligent algorithm-based on CT three-dimensional reconstruction in endoscopic thyroidectomy and perioperative comprehensive nursing

This research was aimed to explore the application of computed tomography (CT) 3D reconstruction technology based on iterative intelligent algorithm in endoscopic thyroidectomy (ET) and perioperative comprehensive nursing. A total of 140 patients with thyroid mass receiving ET were randomly divided into controls (conventional ultrasound combined with perioperative routine nursing) and experimental group (CT 3D reconstruction based on iterative intelligent algorithm combined with perioperative comprehensive nursing), 70 cases in each group. The iterative intelligent algorithm used in this article is an image processing algorithm based on deep learning. Its goal is to generate more accurate and clear 3D reconstructed images by learning and optimizing the original CT images for multiple iterations. The detailed process of the algorithm is as follows: Data preprocessing, Feature extraction and representation, Iterative optimization, 3D reconstruction image generation. Finally, after multiple iterations of optimization, the algorithm will generate high-quality 3D reconstruction images, which can clearly show the anatomical structure of the thyroid mass and the surrounding tissue of the lesion. In order to evaluate the effectiveness of the algorithm, this article recorded the maximum vertical diameter, maximum left and right diameter, and maximum anteroposterior diameter of thyroid masses measured by the two imaging methods and solid specimens. In addition, the postoperative pain of patients was evaluated by visual analogue scale (VAS), and the incidence of complications and nursing satisfaction were counted.

Fuel consumption and trailing-edge noise tradeoff studies via mission-based airfoil shape optimization

Aerodynamic drag is often used as a proxy for fuel consumption in aircraft design. However, the aeroacoustic byproduct of airfoil design, such as trailing-edge noise (TEN), is yet to be considered in aircraft applications, despite its inclusion in wind turbine designs. To explore the impact of TEN in airfoil design for aircraft, we establish a mission-based aerodynamic shape optimization framework. A surrogate-based detailed flight mission analysis (that can simulate a flight mission from takeoff to landing) is incorporated into the optimization framework to obtain realistic flight conditions during takeoff and landing—which are important to assess TEN metrics—and calculate accurate fuel consumption, where both are used to evaluate the objective function. To assess its effectiveness, we compare the results against those of the conventional single-point optimization. Not surprisingly, the mission-based optimization simultaneously reduces fuel consumption and TEN, while the single-point optima (performed at the low Mach region) reduce TEN at the expense of higher fuel consumption. This is due to the tradeoff between aerodynamic performance in the transonic region and aeroacoustic performance in the low Mach region, which cannot be properly analyzed without including flight mission analysis in the optimization loop.

Robust Bayesian target vector optimization for multi-stage manufacturing processes

This research focuses on optimizing multi-stage manufacturing processes using Bayesian optimization (BO) with a robust Expected Improvement (EI) acquisition function. The aim is to optimize towards pre-selected target vectors, not to just minimize or maximize a function. To achieve this, we minimize the Euclidean distance between the actual and target output vectors, which requires transforming the Gaussian surrogate model posterior distribution into a non-central χ2(NCχ2) distribution. Furthermore, the distance measure additionally uses aleatoric uncertainty estimates of the actual output vectors to achieve robustness. We use a cascaded method that also considers the optimization results of intermediate stages, whereby optimization results are propagated from the last stage towards the first stage in each optimization iteration. By considering intermediate process outputs and aleatoric effects, our approach provides a robust optimization method for multi-stage manufacturing processes. To validate our method and to evaluate its properties, we use two artificial use cases. Moreover, we evaluate our approach in an industrial multi-stage forging process for the manufacturing of a nickel basis superalloy turbine disk, where involved stages are represented by corresponding 2D finite element method (FEM) DEFORM simulations. Evaluation suggests that our approach is superior in optimizing multi-stage manufacturing processes by considering all stage outcomes, robust distance measures, and the use of appropriate uncertainty distributions.

Engineering strategies to safely drive CAR T-cells into the future.

Chimeric antigen receptor (CAR) T-cell therapy has proven a breakthrough in cancer treatment in the last decade, giving unprecedented results against hematological malignancies. All approved CAR T-cell products, as well as many being assessed in clinical trials, are generated using viral vectors to deploy the exogenous genetic material into T-cells. Viral vectors have a long-standing clinical history in gene delivery, and thus underwent iterations of optimization to improve their efficiency and safety. Nonetheless, their capacity to integrate semi-randomly into the host genome makes them potentially oncogenic via insertional mutagenesis and dysregulation of key cellular genes. Secondary cancers following CAR T-cell administration appear to be a rare adverse event. However several cases documented in the last few years put the spotlight on this issue, which might have been underestimated so far, given the relatively recent deployment of CAR T-cell therapies. Furthermore, the initial successes obtained in hematological malignancies have not yet been replicated in solid tumors. It is now clear that further enhancements are needed to allow CAR T-cells to increase long-term persistence, overcome exhaustion and cope with the immunosuppressive tumor microenvironment. To this aim, a variety of genomic engineering strategies are under evaluation, most relying on CRISPR/Cas9 or other gene editing technologies. These approaches are liable to introduce unintended, irreversible genomic alterations in the product cells. In the first part of this review, we will discuss the viral and non-viral approaches used for the generation of CAR T-cells, whereas in the second part we will focus on gene editing and non-gene editing T-cell engineering, with particular regard to advantages, limitations, and safety. Finally, we will critically analyze the different gene deployment and genomic engineering combinations, delineating strategies with a superior safety profile for the production of next-generation CAR T-cell.

Two Block Splitting Iteration Methods for Solving Complex Symmetric Linear Systems from Complex Helmholtz Equation

In this paper, we study the improved block splitting (IBS) iteration method and its accelerated variant, the accelerated improved block splitting (AIBS) iteration method, for solving linear systems of equations stemming from the discretization of the complex Helmholtz equation. We conduct a comprehensive convergence analysis and derive optimal iteration parameters aimed at minimizing the spectral radius of the iteration matrix. Through numerical experiments, we validate the efficiency of both iteration methods.

Age of Information-Inspired Data Collection and Secure Upload Assisted by the Unmanned Aerial Vehicle and Reconfigurable Intelligent Surface in Maritime Wireless Sensor Networks

This paper proposes an age of information (AoI)-inspired secure transmissions strategy for secure transmission from the maritime wireless sensor network to the onshore base station (BS) with the assistance of the unmanned aerial vehicle (UAV) and reconfigurable intelligent surface (RIS), in which eavesdroppers exist near the BS. In the proposed scheme, the secure transmission process is divided into the data collection period and the data upload period according to the time sequence to minimize the age of information (AoI) for the privacy information. In the data collection period, we design two scheduling schemes by selecting the sensor with the smallest current AoI or the largest difference in the adjacent AoI. In addition, we propose two heuristic algorithms by adopting the particle swarm optimization algorithm (PSO) and genetic algorithm (GA) to solve the above two problems. In the data uploading period, the uploading time minimization problem is converted to the secrecy rate maximization problem. We design an iterative optimization algorithm with auxiliary variables that are introduced to optimize the reflection coefficient of the RIS. Simulation results show that the proposed scheme can reduce the average AoI by about 10 s compared to the current methods.

Application of ANN in Tourism Business Development for Demand Forecasting and Management of Tourism Headcount

With the rapid development of tourism, it is imperative to forecast tourism demand to maintain the long-term stable development of the tourism industry and make good planning for future tourism enterprises. The study uses the classical model of artificial neural network-BP neural network for tourism number demand prediction, given the problems of traditional BP neural networks, such as prematurity and poor convergence speed, this paper studies the iterative optimization of the algorithm of particle swarm fusion immune mechanism and finds out the optimal network parameters, to build an IAPSO-BP tourism demand prediction model. Tourist amounts from 2007 to 2017 in certain area-related data samples, the training model of iterative speed and fitting effect, and the rolling forecasting method will be used to predict the 2018-2022 years of travel. It can be seen from the convergence curve that the convergence speed of parameter optimization of the IAPSO algorithm is the fastest; the improvedIAPSO-BP network has the best training fitting effect, with a relative average error of 2.03% and an absolute average error of 4.37%, which is better than other forecasting methods. The IAPSO-BP prediction model has higher accuracy and better performance, which can provide an effective basis for the development planning of tourism enterprises and has higher practical application value.

An iterative two-phase optimization method for heterogeneous multi-drone routing problem considering differentiated demands

Owing to low cost, high flexibility and delivery efficiency, effectively addressing the challenges of “last-mile” delivery. While collaborative truck-drone delivery systems have been proposed to overcome limitations such as limited battery life and payload capacity, they are not well-suited for large and heavy parcel delivery. To solve the issue, a pioneering heterogeneous multi-drone delivery system. In this system, the mother drone handles the delivery of large and heavy parcels, releasing small drones to manage the delivery of smaller and lighter parcels. To address the complexities of this multi-drone delivery system, we introduce a divide-and-conquer framework consisting of two integral phases. The first phase, the task allocation phase, generates multiple task allocation schemes, while the second phase, the single-drone route planning phase, produces high-quality routes for each individual drone. Two phases are performed in an iterative manner until the predefined stopping criteria are satisfied. In the task allocation phase, we propose a simulated annealing algorithm (SA) to facilitate task allocation among multiple drones, utilizing transfer and recombination operators to generate high-quality solutions. After obtaining the task allocation scheme, a satisfactory route of a mother drone is generated by a variable neighborhood descent algorithm (VND). A desirable route for each single small drone is produced by dynamic programming (DP).Extensive experiments are conducted, demonstrating the outstanding optimization and time efficiency of the proposed two-phase optimization method by the fact that it obtains within a 4.89% gap from the optimal solution generated by CPLEX in 15.48 s for instance up to 125 nodes.

Optimal loop power flow control of power distribution system using advanced meta-heuristic algorithms

Optimal loop power flow control of power distribution system using advanced meta-heuristic algorithms

Influence of Image Compositing and Multisource Data Fusion on Multitemporal Land Cover Mapping of Two Philippine Watersheds

Cloud-based remote sensing has spurred the use of techniques to improve mapping accuracy where individual images may have lower quality, especially in areas with complex terrain or high cloud cover. This study investigates the influence of image compositing and multisource data fusion on the multitemporal land cover mapping of the Pagsanjan-Lumban and Baroro Watersheds in the Philippines. Ten random forest models for each study site were used, all using a unique combination of more than 100 different input features. These features fall under three general categories. First, optical features were derived from reflectance bands and ten spectral indices, which were further subdivided into annual percentile and seasonal median composites; second, radar features were derived from ALOS PALSAR by computing textural indices and a simple band ratio; and third, topographic features were computed from the ALOS GDSM. Then, accuracy metrics and McNemar’s test were used to assess and compare the significance of about 90 pairwise model outputs. Data fusion significantly improved the accuracy of multitemporal land cover mapping in most cases. However, image composition had varied impacts for both sites. This could imply local characteristics and feature inputs as potential determinants of the ideal composite method. Hence, the iterative screening or optimization of both input features and composites is recommended to improve multitemporal mapping accuracy.

Energy-saving design of azeotropic distillation for the separation of methanol–methyl methacrylate azeotrope from industrial effluent

For the purpose of separating the binary methanol–methyl methacrylate (MMA) azeotrope in light boiling residues and preventing MMA polymerization from acetone cyanohydrin process, low pressure heterogeneous azeotropic distillation (HAD) with process intensification was adopted. The binary interaction parameters of the azeotrope were obtained by correlating and regressing the experimental data of isobaric vapor–liquid equilibrium at low pressures (75, 50 and 26 kPa for methanol-MMA and 26 kPa for cyclohexane-MMA). The residue curve map at 26 kPa was plotted under the UNIQUAC model, and the optimal parameters of its conventional process were achieved through sequential iterative optimization procedure. The purity of MMA and methanol was 99.99 wt% and 99.90 wt%, respectively. Subsequently, in order to further reduce costs and energy consumption, dividing wall column (ADWC), heat pump distillation (HP-AD), and heat pump assisted azeotropic dividing wall column (HP-ADWC), three technical approaches were explored and compared. Total annual cost (TAC), total energy consumption (TEC), and CO2 emissions were used as evaluation indicators. Among them, ADWC reduced its annual capital investment by 14.48 % through special structural design. HP-AD effectively reduced TEC by 27.30 %. HP-ADWC combined the advantages of both, effectively reducing costs and saving energy (12.88 % in TAC). At present, the purity and energy saving of the product meet industrial expectations, providing valuable insights for enhanced methanol-MMA azeotrope recovery from industrial effluent.

3D Reconstruction Based on Iterative Optimization of Moving Least-Squares Function

3D Reconstruction Based on Iterative Optimization of Moving Least-Squares Function

Empowering Light Fidelity-Enabled Internet of Things with Hybrid Fuzzy-Particle Swarm Optimization Power Allocation for Enhanced Energy Efficiency and Quality of Service

This paper proposes a hybrid fuzzy-Particle Swarm Optimization (PSO) approach for power allocation in bidirectional Light Fidelity (LiFi)-enabled Internet of Things (IoT) communication systems. The approach integrates fuzzy logic and PSO to achieve efficient and robust power allocation, considering energy efficiency and Quality of Service (QoS) requirements. The hybrid approach leverages flexibility of fuzzy logic to handle uncertainties and variations in system parameters, such as channel conditions and QoS requirements. Fuzzy sets and membership functions are defined to represent linguistic variables, and fuzzy rules are formulated based on expert knowledge and system-specific considerations. This allows the approach to adaptively adjust power allocation based on varying channel conditions and QoS requirements, enhancing the robustness of the power allocation strategy. The PSO algorithm is employed for iterative optimization to explore for ideal power allocation solution. The particles in swarm signify possible power allocation configuration, and its position in the search space corresponds to a specific power allocation. The particles update their positions based on local best-known positions and globally best-known positions, allowing the swarm to converge toward the optimal solution. Through extensive simulations and analysis, the proposed hybrid fuzzy-PSO approach is evaluated with regard to energy efficiency and QoS satisfaction. The results demonstrate its effectiveness in achieving energy-efficient power allocation while meeting diverse QoS requirements. The proposed approach outperforms existing methods such as channel- and Orthogonal Multiple Access (OMA)-based power allocation schemes.