Multimodal Data-Driven Reinforcement Learning for Operational Decision-Making in Industrial Processes

Dear Editor, This letter proposes a multimodal data-driven reinforcement learning-based method for operational decision-making in industrial processes. Due to the frequent fluctuations of feedstock properties and operating conditions in the industrial processes, existing data-driven methods cannot effectively adjust the operational variables. In addition, multimodal data such as images, audio.

An extended state observer with adjustable bandwidth for measurement noise

In this paper,a bandwidth-adjustable extended state observer(ABESO)is proposed for the systems with measurement noise.It is known that increasing the bandwidth of the observer improves the tracking speed but tolerates noise,which conflicts with observation accuracy.Therefore,we introduce a bandwidth scaling factor such that ABESO is formulated to a 2-degree-of-freedom system.The observer gain is determined and the bandwidth scaling factor adjusts the bandwidth according to the tracking error.When the tracking error decreases,the bandwidth decreases to suppress the noise,otherwise the bandwidth does not change.It is proven that the error dynamics are bounded and converge in finite time.The relationship between the upper bound of the estimation error and the scaling factor is given.When the scaling factor is less than 1,the ABESO has higher estimation accuracy than the linear extended state observer(LESO).Simulations of an uncertain nonlinear system with compound disturbances show that the proposed ABESO can successfully estimate the total disturbance in noisy environments.The mean error of total disturbance of ABESO is 15.28% lower than that of LESO.

Research on Demand Response Potential of Adjustable Loads in Demand Response Scenarios

To address the issues of limited demand response data,low generalization of demand response potential evaluation,and poor demand response effect,the article proposes a demand response potential feature extraction and prediction model based on data mining and a demand response potential assessment model for adjustable loads in demand response scenarios based on subjective and objective weight analysis.Firstly,based on the demand response process and demand response behavior,obtain demand response characteristics that characterize the process and behavior.Secondly,establish a feature extraction and prediction model based on data mining,including similar day clustering,time series decomposition,redundancy processing,and data prediction.The predicted values of each demand response feature on the response day are obtained.Thirdly,the predicted data of various characteristics on the response day are used as demand response potential evaluation indicators to represent different demand response scenarios and adjustable loads,and a demand response potential evaluation model based on subjective and objective weight allocation is established to calculate the demand response potential of different adjustable loads in different demand response scenarios.Finally,the effectiveness of the method proposed in the article is verified through examples,providing a reference for load aggregators to formulate demand response schemes.

Differential pressure difference based altitude control of a stratospheric satellite

An autonomous altitude adjustment system for a stratospheric satellite(StratoSat)platform is proposed.This platform consists of a helium balloon,a ballonet,and a two-way blower.The helium balloon generates lift to balance the platform gravity.The two-way blower inflates and deflates the ballonet to regulate the buoyancy.Altitude adjustment is achieved by tracking the differential pressure difference(DPD),and a threshold switching strategy is used to achieve blower flow control.The vertical acceleration regulation ability is decided not only by the blower flow rate,but also by the designed margin of pressure difference(MPD).Pressure difference is a slow-varying variable compared with altitude,and it is adopted as the control variable.The response speed of the actuator to disturbance can be delayed,and the overshoot caused by the large inertia of the platform is inhibited.This method can maintain a high tracking accuracy and reduce the complexity of model calculation,thus improving the robustness of controller design.

Research and Practice on the Construction of Professional Cluster in Application-Oriented Local Undergraduate Universities:Taking Environ-mental Chemical Engineering Professional Cluster in Pingdingshan University as an Example

Based on the analysis of the importance of professional cluster construction by ecological theory,with the change of social demand for talents,this paper explores the practice of environmental chemical professional cluster construction in Pingdingshan University,including gradually perfecting teaching conditions and reforming teaching mode,breaking through the limitations of resources,integrating the boundaries of colleges and departments,integrating multiple resources,innovating systems and mechanisms,reconstructing professional clusters,decon-structing professional connotations,reorganizing curriculum systems,etc.,in order to better build the ecological chain network of education in application-oriented colleges and universities,realize the deep integration of industry and education,train future-oriented interdisciplinary applied talents of new engineering,and realize the construction of characteristic professional cluster in application-oriented colleges.

Cross-Cultural Adjustment and Coping:U.S.Students in Taiwan Residents Higher Education

The aim of this study was to investigate the adjustment problems of students from the United States enrolled in universities in the East,specifically in Taiwan,their problems related to cultural adaptation,and the process of adjustment to student life in Taiwan.Under investigation were cultural adjustment and coping skills as these students transitioned from West to East.Qualitative data were collected from interviews with participants and faculty members as well as participant observations.Results indicated that U.S.students found their own ways to acclimate to their new academic setting as well as to social relations,cross-cultural issues,and the linguistic environment in Taiwan to achieve effective adaptation.They made changes in themselves to cope with all situations they encountered.This study provides suggestions for international students abroad in Taiwan,for the Taiwan Residents government,and for universities or colleges in terms of what they should offer to current and future international students.

Optimized CUDA Implementation to Improve the Performance of Bundle Adjustment Algorithm on GPUs

The 3D reconstruction pipeline uses the Bundle Adjustment algorithm to refine the camera and point parameters. The Bundle Adjustment algorithm is a compute-intensive algorithm, and many researchers have improved its performance by implementing the algorithm on GPUs. In the previous research work, “Improving Accuracy and Computational Burden of Bundle Adjustment Algorithm using GPUs,” the authors demonstrated first the Bundle Adjustment algorithmic performance improvement by reducing the mean square error using an additional radial distorting parameter and explicitly computed analytical derivatives and reducing the computational burden of the Bundle Adjustment algorithm using GPUs. The naïve implementation of the CUDA code, a speedup of 10× for the largest dataset of 13,678 cameras, 4,455,747 points, and 28,975,571 projections was achieved. In this paper, we present the optimization of the Bundle Adjustment algorithm CUDA code on GPUs to achieve higher speedup. We propose a new data memory layout for the parameters in the Bundle Adjustment algorithm, resulting in contiguous memory access. We demonstrate that it improves the memory throughput on the GPUs, thereby improving the overall performance. We also demonstrate an increase in the computational throughput of the algorithm by optimizing the CUDA kernels to utilize the GPU resources effectively. A comparative performance study of explicitly computing an algorithm parameter versus using the Jacobians instead is presented. In the previous work, the Bundle Adjustment algorithm failed to converge for certain datasets due to several block matrices of the cameras in the augmented normal equation, resulting in rank-deficient matrices. In this work, we identify the cameras that cause rank-deficient matrices and preprocess the datasets to ensure the convergence of the BA algorithm. Our optimized CUDA implementation achieves convergence of the Bundle Adjustment algorithm in around 22 seconds for the largest dataset compared to 654 seconds for the sequential implementation, resulting in a speedup of 30×. Our optimized CUDA implementation presented in this paper has achieved a 3× speedup for the largest dataset compared to the previous naïve CUDA implementation.

Research of Future Directions and Considerations for Implementation of the Forest City Strategy

A “Forest City” (FC) is an urban area that has a significant amount of forest cover. It is now a green urban development strategy that is supported by numerous nations. This essay compares the many FC implementation strategies used in developed and developing countries and explores potential future paths for this tactic. The variations between FC in terms of measurement targets, air purification, street trees, and forestry development are thoroughly compared in this research. This essay goes on to explore FC’s potential in the future regarding policy changes and the environment based on this comparison. Therefore, this essay focuses on the necessity of considering industrial innovation, encouraging biodiversity, lowering greenhouse gas emissions, paying attention to forest restructuring, and being more responsive to the issues provided by urbanization in the future global implementation of FC.

Temperature-Based Fan Speed Optimization Strategy

As energy efficiency and indoor comfort increasingly become key standards in modern residential and office environments,research on intelligent fan speed control systems has become particularly important.This study aims to develop a temperature-feedback-based fan speed optimization strategy to achieve higher energy efficiency and user comfort.Firstly,by analyzing existing fan speed control technologies,their main limitations are identified,such as the inability to achieve smooth speed transitions.To address this issue,a BP-PID speed control algorithm is designed,which dynamically adjusts fan speed based on indoor temperature changes.Experimental validation demonstrates that the designed system can achieve smooth speed transitions compared to traditional fan systems while maintaining stable indoor temperatures.Furthermore,the real-time responsiveness of the system is crucial for enhancing user comfort.Our research not only demonstrates the feasibility of temperature-based fan speed optimization strategies in both theory and practice but also provides valuable insights for energy management in future smart home environments.Ultimately,this research outcome will facilitate the development of smart home systems and have a positive impact on environmental sustainability.

Research on Biometric Identification Method of Nuclear Cold Source Disaster Based on Deep Learning

In this paper, an improved Fast-R-CNN nuclear power cold source disaster biological image recognition algorithm is proposed to improve the safety operation of nuclear power plants. Firstly, the image data sets of the disaster-causing creatures hairy shrimp and jellyfish were established. Then, in order to solve the problems of low recognition accuracy and unrecognizable small entities in disaster biometrics, Gamma correction algorithm was used to optimize the image of the data set, improve the image quality and reduce the noise interference. Transposed convolution is introduced into the convolution layer to increase the recognition accuracy of small targets. The experimental results show that the recognition rate of this algorithm is 6.75%, 7.5%, 9.8% and 9.03% higher than that of ResNet-50, MobileNetv1, GoogleNet and VGG16, respectively. The actual test results show that the accuracy of this algorithm is obviously better than other algorithms, and the recognition efficiency is higher, which basically meets the preset requirements of this paper.

A Self-calibration Bundle Adjustment Algorithm Based on Block Matrix Cholesky Decomposition Technology

In this study,the problem of bundle adjustment was revisited,and a novel algorithm based on block matrix Cholesky decomposition was proposed to solve the thorny problem of self-calibration bundle adjustment.The innovation points are reflected in the following aspects:①The proposed algorithm is not dependent on the Schur complement,and the calculation process is simple and clear;②The complexities of time and space tend to O(n)in the context of world point number is far greater than that of images and cameras,so the calculation magnitude and memory consumption can be reduced significantly;③The proposed algorithm can carry out self-calibration bundle adjustment in single-camera,multi-camera,and variable-camera modes;④Some measures are employed to improve the optimization effects.Experimental tests showed that the proposed algorithm has the ability to achieve state-of-the-art performance in accuracy and robustness,and it has a strong adaptability as well,because the optimized results are accurate and robust even if the initial values have large deviations from the truth.This study could provide theoretical guidance and technical support for the image-based positioning and 3D reconstruction in the fields of photogrammetry,computer vision and robotics.

Vertical deformation analysis based on combined adjustment for GNSS and leveling data

A method is proposed to fuse the velocity data of the global navigation satellite system(GNSS) and leveling height via combined adjustment with constraints. First, stable GNSS-leveling points are uniformly selected, and the constraints of the geodetic height change velocity and normal height change velocity are given. Then, the GNSS vertical velocities and leveling height difference are used as observations of combined adjustment, and robust least-squares estimation are used to estimate the velocities of the unknown points. Finally, a vertical movement model is established with the GNSS vertical velocities and leveling vertical velocities obtained via combined adjustment. Data from the second-order leveling network and GNSS control points in Shandong Province are taken as test data, and eight calculation schemes are used for discussion. One of the schemes, the bifactor robust combined adjustment method based on variance component estimation with two kinds of vertical velocity constraints achieves the optimal results. The method applied in the scheme can be recommended for data fusion of GNSS and leveling, further improving the reliability of vertical crustal movement in Shandong Province.

Reconfigurable source illusion device for airborne sound using an enclosed adjustable piezoelectric metasurface

Source illusion is an important issue in acoustic fields that has significant applications in various practical scenarios.Recent progress in acoustic metasurfaces has broken the limitation of manipulating large-scale waves at subwavelength scales and enables a better illusion capability,while there is still a problem that most previous studies are hampered by a lack of tuning capability.Here we propose a reconfigurable source illusion device capable of providing azimuthallydependent phase delay in real-time via changing the static voltage distribution.The resulting device is implemented by employing an adjustable piezoelectric metasurface with a subwavelength thickness that can achieve a full 2π-phase shift while maintaining efficient transmittance.The effectiveness of our mechanism is demonstrated via two distinctive source illusion phenomena of shifting and transforming a simple point source without changing the device geometry.We anticipate that our methodology,which does not require a large device size or a complicated phased array,will open up new avenues for the miniaturization and integration of source illusion devices and may promote their on-chip applications in a variety of fields,such as acoustic camouflage and manipulation precision.

DROUGHT-INDUCED UNKNOWN PROTEIN 1 positively modulates drought tolerance in cultivated alfalfa(Medicago sativa L.)

Alfalfa is the most widely cultivated perennial legume forage crop worldwide.Drought is one of the major environmental factors influencing alfalfa productivity.However,the molecular mechanisms underlying alfalfa responses to drought stress are still largely unknown.This study identified a drought-inducible gene of unknown function,designated as Medicago sativa DROUGHT-INDUCED UNKNOWN PROTEIN 1(MsDIUP1).MsDIUP1 was localized to the nucleus,chloroplast,and plasma membranes.Overexpression of MsDIUP1 in Arabidopsis resulted in increased tolerance to drought,with higher seed germination,root length,fresh weight,and survival rate than in wild-type(WT)plants.Consistently,analysis of MsDIUP1 over-expression(OE)alfalfa plants revealed that MsDIUP1 also increased tolerance to drought stress,accompanied by physiological changes including reduced malondialdehyde(MDA)content and increased osmoprotectants accumulation(free proline and soluble sugar),relative to the WT.In contrast,disruption of MsDIUP1 expression by RNA interference(RNAi)in alfalfa resulted in a droughthypersensitive phenotype,with a lower chlorophyll content,higher MDA content,and less osmoprotectants accumulation than that of the WT.Transcript profiling of alfalfa WT,OE,and RNAi plants during drought stress showed differential responses for genes involved in stress signaling,antioxidant defense,and osmotic adjustment.Taken together,these results reveal a positive role for MsDIUP1 in regulating drought tolerance.

Adaptive Graph Embedding With Consistency and Specificity for Domain Adaptation

Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabeled target samples well.Existing approaches leverage Graph Embedding Learning to explore such a subspace. Unfortunately, due to 1) the interaction of the consistency and specificity between samples, and 2) the joint impact of the degenerated features and incorrect labels in the samples, the existing approaches might assign unsuitable similarity, which restricts their performance. In this paper, we propose an approach called adaptive graph embedding with consistency and specificity(AGE-CS) to cope with these issues. AGE-CS consists of two methods, i.e., graph embedding with consistency and specificity(GECS), and adaptive graph embedding(AGE).GECS jointly learns the similarity of samples under the geometric distance and semantic similarity metrics, while AGE adaptively adjusts the relative importance between the geometric distance and semantic similarity during the iterations. By AGE-CS,the neighborhood samples with the same label are rewarded,while the neighborhood samples with different labels are punished. As a result, compact structures are preserved, and advanced performance is achieved. Extensive experiments on five benchmark datasets demonstrate that the proposed method performs better than other Graph Embedding methods.

Optimal Bottleneck-Driven Deep Belief Network Enabled Malware Classification on IoT-Cloud Environment

Cloud Computing(CC)is the most promising and advanced technology to store data and offer online services in an effective manner.When such fast evolving technologies are used in the protection of computerbased systems from cyberattacks,it brings several advantages compared to conventional data protection methods.Some of the computer-based systems that effectively protect the data include Cyber-Physical Systems(CPS),Internet of Things(IoT),mobile devices,desktop and laptop computer,and critical systems.Malicious software(malware)is nothing but a type of software that targets the computer-based systems so as to launch cyberattacks and threaten the integrity,secrecy,and accessibility of the information.The current study focuses on design of Optimal Bottleneck driven Deep Belief Network-enabled Cybersecurity Malware Classification(OBDDBNCMC)model.The presentedOBDDBN-CMCmodel intends to recognize and classify the malware that exists in IoT-based cloud platform.To attain this,Zscore data normalization is utilized to scale the data into a uniform format.In addition,BDDBN model is also exploited for recognition and categorization of malware.To effectually fine-tune the hyperparameters related to BDDBN model,GrasshopperOptimizationAlgorithm(GOA)is applied.This scenario enhances the classification results and also shows the novelty of current study.The experimental analysis was conducted upon OBDDBN-CMC model for validation and the results confirmed the enhanced performance ofOBDDBNCMC model over recent approaches.

Novel Radiation-Adjustable Heating Terminal Based on Flat Heat Pipe Combined with Air Source Heat Pump

The electrification of building heating is an effective way to meet the global carbon target. As a clean and sustainable electrified heating technology, air-source heat pumps (ASHPs) are widely used in areas lacking central heating. However, as a major component of space heating, heating terminals might not fit well with ASHP in order to achieve both intermittency and comfort. Therefore, this study proposes a novel radiation-adjustable heating terminal combined with an ASHP to achieve electrification, intermittency, and better thermal comfort. Radiant terminals currently suffer from three major problems: limited maximum heating capacity, inability to freely adapt, and difficulty with combining them with ASHPs. These problems were solved by improving the structural design of the novel terminal (Improvement A–E). Results showed that the maximum heating capacity increased by 23.6% and radiation heat transfer ratio from 10.1% to 30.9% was provided for users with the novel terminal. Further, new flat heat pipe (FHP) design improved stability (compressor oil return), intermittency (refrigerant thermal inertia), and safety (refrigerant leakage risk) by reducing the length of exposed refrigerant pipes. Furthermore, a new phased operation strategy was proposed for the novel terminal, and the adjustability of the terminal was improved. The results can be used as reference information for decarbonizing buildings by electrifying heating terminals.

Characteristics of gravity anomalies and tectonic analysis of Enderby Land in East Antarctica and its adjacent areas

Enderby Land in East Antarctica and its adjacent areas,which are closely related to the Indian Plate in their geological evolution,have become one of the key zones for studies on how the Antarctic continent evolves.Based on the isostasy and flexure theories of the lithosphere and using the CRUST1.0 model as the depth constraint,this paper uses the gravity field model EIGEN-6C4 and topographic data to calculate the isostatic gravity anomalies of Enderby Land and its adjacent areas.Then,the crustal thickness of the study area is calculated,and three comprehensive geophysical interpretation profiles that vertically span the study area are plotted.The results show that the flexural isostatic gravity anomalies in Enderby Land and its adjacent areas are closely related to the regional tectonic setting,and the anomalies in different regions differ substantially,ranging from−50×10^(−5)m/s^(2)to 85×10^(−5)m/s^(2).A zone of high isostatic gravity anomalies(30×10^(−5)−80×10^(−5)m/s^(2))is distributed outside the Cooperation Sea and Queen Maud Land,which may be plate remnants generated by early rifting.Except for the Kerguelen Plateau,which was formed by a hotspot and has a crustal thickness of 15 km,the thickness of the oceanic crust in other parts of the study area changes slightly by approximately 4–9 km,with the thinnest part being in Enderby Basin.The thickness of the inland crust along the coastline increases with the elevation,with the maximum thickness reaching 34 km.The isostatic gravity anomalies corresponding to the zone of high magnetic anomalies along the continental margin of Queen Maud Land are negative and small,with an isostatic adjustment trend indicating Moho surface uplift,and those on the edge of central Enderby Land are near zero,approaching the isostatic state,which may be caused by the magmatism at the early stage of rifting.The continental-oceanic boundary should be close to the contour line of the crustal thickness 10–12 km on the outer edge of the coastline.

Verification of Depth Adjustment Factor in Eurocode 5 for Tropical Hardwood Timbers

The depth adjustment factor for bending strength stated in Eurocode 5(EC5)is only applicable to timbers having a characteristic density below 700 kg/m^(3).However,most Malaysian timbers are hardwood,some with a characteristic density reaching above 700 kg/m^(3).Therefore,the objective of this study was to examine whether the depth adjustment factor stipulated in EC5 is valid for Malaysian hardwood timbers.Six timber species were selected for this study,namely Kapur(Dryobalanops C.F.Gaertn.),Kempas(Koompassia Maingay ex Benth.),Keruing(Dipterocarpus C.F.Gaertn.),Light red meranti(Shorea Roxb.ex C.F.Gaertn.),Geronggang(Cratoxylum Blume)and Balau(Shorea Roxb.ex C.F.Gaertn.).The determination of bending strength and characteristic density was conducted according to BS EN 408:2010 and BS EN 384:2016,respectively.A graph for mean bending strength vs.(150/h)was plotted for each timber species.The power function was selected to analyze the relationship between the two variables.The power of the regression equations varied depending on the characteristic density of the timber species.For species with a characteristic density below 700 kg/m^(3),such as Kapur,Keruing,and Light red meranti,the power was between 0.16 to 0.17.In contrast,for species having a characteristic density above 700 kg/m^(3),namely Kempas and Balau,the power was higher at 0.23 and 0.24,respectively.Geronggang was an exception to this pattern.These values are close to the depth adjustment factor given in EC5,which is 0.2.Based on the results,it can be suggested that the adjustment factor of 0.2 is also applicable to Malaysian hardwood timbers with a characteristic density above 700 kg/m^(3).

Physiological Changes in Leaves of Medicago falcata Under Low-Temperature Stress

Low temperature significantly restricts crop yield and quality.Medicago falcata(M.falcata)is a typical legume species that exhibits great capacity of tolerance to low temperature.To understand the low-temperature responses in M.falcata,the electrolyte leakage and lipid peroxidation level,and activities of superoxide dismutase(SOD),catalase(CAT)and peroxidase(POD),and contents of reduced glutathione(GSH),soluble protein,soluble sugar and proline were investigated in low-temperature-stressed M.falcata leaves.The electrolyte leakage and malondialdehyde(MDA)content increased,and could be used to quantify low-temperature damage at cellular level.And then,the significant change of SOD,POD and CAT activities,and GSH content reflected the higher reactive oxygen species(ROS)scavenging capacity in M.falcata.In addition,the significant change of soluble protein,soluble sugar and proline contents helped to maintain osmotic equilibrium,energy supply and protein functions.These nine physiological traits were analyzed by gray relational grade analysis and ranked from the highest to the lowest as follows:electrolyte leakage,GSH,proline,soluble protein,MDA,soluble sugar,SOD,CAT and POD,and illustrated that the electrolyte leakage level,GSH and proline contents should be selected and measured priority in M.falcata low-temperature tolerance to improve measurement efficiency.