Auxiliary Model Research Articles

WSCC: A Weight-Similarity-Based Client Clustering Approach for Non-IID Federated Learning

The fast development of the Internet of Things (IoT) and deep learning enables learning useful patterns from the massive amount of collected data with sporadic nodes in IoT systems. Federated learning has received increasing attention in distributed machine learning where only intermediate parameters are exchanged with training samples that resided at local nodes. Nonetheless, most of the existing federated learning schemes assume a homogeneous distribution of data. The assumption, however, does not apply to IoT systems because of the heterogeneity of the IoT architecture. The nonindependent and identical distribution (non-IID) property in data volume and statistical distribution of IoT nodes can impact the performance of an aggregated global model that fits all nodes. Existing federated learning solutions for non-IID data sets either have to train additional models or require extra data exchange to check the node distribution. However, due to resource constraints in IoT systems, these approaches will increase the burden on limited computation capacity and cause network overhead. To address the issue, in this article, a novel weight-similarity-based client clustering (WSCC) approach is proposed, in which clients are split into different groups based on their data set distributions. An affinity-propagation-based method with the cosine distance of the client’s weight parameters is designed to iteratively and automatically determine dynamic clusters. The proposed approach is ideal for IoT systems since there are no auxiliary models and extra data transmissions are needed. Through the theoretical convergence analysis and empirical results, we show that our proposed WSCC scheme outperforms the representative federated learning schemes under different non-IID settings, achieving up to 20% improvements in accuracy.

A Novel Deterministic Threshold Proxy Re-Encryption Scheme From Lattices

Aiming at the problem that it is difficult to flexibly realize, the sharing and efficient search of encrypted data in large data-bases, this paper proposes a deterministic threshold proxy re-encryption scheme under the auxiliary input model. This scheme uses Shamir's secret sharing technology to achieve threshold control, uses homomorphic signature technology to verify the legitimacy of ciphertext, and applies deterministic algorithms to solve the search problem in large databases, while ensuring the user's control over their own data, and proves its security can reach indistinguishable semantic security (PRIV1-INDr) under the standard model. Compared with other schemes, this scheme not only shortens the length of the ciphertext and improves the decryption efficiency, but it also has anti-auxiliary input, robustness, and multi-hop characteristics and can better meet actual needs.

EAGS: An extracting auxiliary knowledge graph model in multi-turn dialogue generation.

Multi-turn dialogue generation is an essential and challenging subtask of text generation in the question answering system. Existing methods focused on extracting latent topic-level relevance or utilizing relevant external background knowledge. However, they are prone to ignore the fact that relying too much on latent aspects will lose subjective key information. Furthermore, there is not so much relevant external knowledge that can be used for referencing or a graph that has complete entity links. Dependency tree is a special structure that can be extracted from sentences, it covers the explicit key information of sentences. Therefore, in this paper, we proposed the EAGS model, which combines the subjective pivotal information from the explicit dependency tree with sentence implicit semantic information. The EAGS model is a knowledge graph enabled multi-turn dialogue generation model, and it doesn’t need extra external knowledge, it can not only extract and build a dependency knowledge graph from existing sentences, but also prompt the node representation, which is shared with Bi-GRU each time step word embedding in node semantic level. We store the specific domain subgraphs built by the EAGS, which can be retrieved as external knowledge graph in the future multi-turn dialogue generation task. We design a multi-task training approach to enhance semantics and structure local feature extraction, and balance with the global features. Finally, we conduct experiments on Ubuntu large-scale English multi-turn dialogue community dataset and English Daily dialogue dataset. Experiment results show that our EAGS model performs well on both automatic evaluation and human evaluation compared with the existing baseline models.

Active disturbance rejection control for optoelectronic stabilized platform based on model-assisted double extended state observers

PurposeThis study aims to promote the anti-disturbance and tracking accuracy of optoelectronic stabilized platforms, which ensure that optical detectors accurately track targets and acquire high-quality images.Design/methodology/approachAn improved active disturbance rejection control (ADRC) strategy based on model-assisted double extended state observers (MDESOs) is proposed in this paper. First, by establishing an auxiliary model, the total disturbances are separated into two parts: inner and external disturbances. Then, MDESOs are designed to estimate the two parts by separately using two parallel ESOs, by which the controlled plant is adjusted to the ideal pure integral series. Simultaneously, combined with the nonlinear state error feedback, an overall control strategy is established.FindingsCompared with the conventional ADRC and proportional derivative, the improved ADRC (IADRC) has stronger robustness and adaptability and effectively reduces the requirements for model accuracy and the gain of the ESO. The error of the auxiliary model is tolerated to exceed 50%, and the parameter values of the MDESOs are reduced by 90%.Originality/valueThe total disturbance rejection rate of the proposed strategy is only 3.11% under multiple disturbances, which indicates that the IADRC strategy significantly promotes anti-disturbance performance.

Robust possibilistic programming to design a closed-loop blood supply chain network considering service-level maximization and lateral resupply.

Reconfiguring the structure of the supply chain network is one of the most strategic and vital decisions in designing a supply chain network. In this study, a Closed-Loop Blood Supply Chain Network (CLBSCN) considering blood group compatibility, ABO-Rh(D), and blood product shelf life has been studied to determine the best strategic and tactical decisions simultaneously considering lateral resupply/transshipment and service-level maximization. Several vital parameters, including supply and demand, are considered fuzzy numbers to approximate reality due to the nature of the world. Furthermore, two crucial factors include ABO-Rh(D) and blood product shelf life considered, while the concept of lateral resupply governs the interconnections of hospitals’ excess blood units. We propose a fuzzy multi-objective Mixed-Integer Non-Linear Programming (MINLP) model to consider two critical objective functions: minimizing the total costs of the network and maximizing the minimum service level to the patients at each Hospital. The fuzzy multi-objective MINLP model is converted to a deterministic multi-objective model using the equivalent auxiliary crisp model to deal with uncertainty. Then, by utilizing two interactive fuzzy solution approaches, the results have been compared based on a real case study to suggest the best solution for the proposed model. Also, we conduct sensitivity analysis on essential parameters such as demand, supply, and capacity to understand how these parameter variations impact two proposed objective functions. Then, the proposed model is tested on a real case study for model validation. The results confirmed that considering the lateral resupply could significantly save the costs of the designed network by a total of $343,000. Interestingly, maximizing the minimum service level at hospitals increased the service level from 58% to 68%.

Wiener models robust identification of multi-rate process with time-varying delay using expectation-maximization algorithm

Multi-rate systems exist widely in the field of computer process control. Research on the multi-rate issue of linear systems is relatively mature and is gradually turning to multi-rate issues of nonlinear systems. Concurrently, irregular process disturbances (impulse noise, outliers, non-zero mean noise) and varying transmission delay problems are often overlooked or considered alone, which is lacking generality. Thus, the main objective of this paper is to formulate and solve the identification problem of multi-rate nonlinear Wiener models with time-varying delay and irregular process disturbances simultaneously. The probability graph model of the Wiener process is constructed. Under the expectation–maximization (EM) framework, the Scale outlier model and Location outlier model (both based on Gaussian mixture distribution) are separately introduced to model the contaminated output data. The time-varying delay at each sampling instant is assumed as a uniform distribution. An auxiliary model is applied to acquire the unmeasured middle variable. Then, a robust EM identification algorithm is developed and its convergence is analyzed. The validity of the developed approach is illustrated through two numerical examples and a simulation of the continuous stirred tank reactor.

Extension of as-if-Markov modeling to scaled payments

In multi-state life insurance, as-if-Markov modeling has recently been suggested as an alternative to Markov modeling in case of deterministic sojourn and transition payments. Incidental policyholder behavior, on the other hand, gives rise to duration-dependent payments in the form of so-called scaled payments. The goal of this paper is to establish as-if-Markov modeling also for scaled payments. To this end, we employ change of measure techniques to transfer the added complexity from the payments to an auxiliary probabilistic model. Based hereon, we show how to compute the accumulated cash flow by solving a system of equations comparable to Kolmogorov's forward equations for Markov chains, but with the transition rates replaced by certain forward transition rates related to the auxiliary probabilistic model. Finally, we provide feasible landmark estimators for these auxiliary forward transition rates subject to entirely random right-censoring.

Pulsar candidate selection with residual convolutional autoencoder

ABSTRACT The pulsar detection survey has contributed to the study of celestial evolution by providing scientists with a large amount of observational data. In addition, the amount of data collected by the survey has grown exponentially, and there is a large class imbalance in the corresponding data. In this paper, we design a residual convolutional autoencoder (RCAE) based on the structure of the autoencoder, and combine with logistic regression (LR) to construct a network structure framework suitable for pulsar candidate identification. RCAE is used as the primary model to fit the data distribution of the non-pulsar sample, the process does not need to consider the positive and negative pulsar sample imbalance. LR is used as an auxiliary classification model to test the final results. The experimental results on the HTRU Medlat and PMPS-26k data sets show that the best performance is achieved without the use of data generation and complex enhancement methods.

Gas Leakage Recognition Based on Wide-Band Infrared Imaging with the Auxiliary Excitation Method and Machine Learning Model

Gas Leakage Recognition Based on Wide-Band Infrared Imaging with the Auxiliary Excitation Method and Machine Learning Model

Design of auxiliary model based normalized fractional gradient algorithm for nonlinear output-error systems

A new avenue of fractional calculus applications has emerged that investigates the design of fractional gradient based novel iterative methods for analyzing fractals and nonlinear dynamics in solving engineering and applied sciences problems. The most discussed algorithm in this regard is fractional least mean square (FLMS) algorithm. This study presents an auxiliary model based normalized variable initial value FLMS (AM-NVIV-FLMS) algorithm for input nonlinear output error (INOE) system identification. First, NVIV-FLMS is presented to automatically tune the learning rate parameter of VIV-FLMS and then the AM-NVIV-FLMS is introduced by incorporating the auxiliary model idea that replaces the unknown values of the information vector with the output of auxiliary model. The proposed AM-NVIV-FLMS scheme is accurate, convergent, robust and reliable for INOE system identification. Simulation results validate the significance and efficacy of the proposed scheme.

Hybrid simulation method with restoring force correction for structural testing characterized by incomplete boundary conditions

AbstractHybrid simulation is a powerful testing method that combines numerical analysis and physical experiments through on‐line interaction. The substructuring technology enables hybrid simulation to evaluate the structural performance with large‐scale specimens. However, this technology also increases the complexity of specimen boundary conditions. Due to limited equipment resources of structural laboratories, not all the degrees of freedom of the boundary conditions can be realized during tests, which will induce error to the experimental restoring forces and decrease of accuracy of hybrid simulation. In this case, the hybrid simulation method based on restoring force correction was proposed to reduce this error. In this method, the error in experimental restoring forces were corrected using an auxiliary numerical model of the experimental substructure. The effectiveness of the proposed method was verified through both theoretical analysis and numerical examples. This method was then adopted to evaluate the seismic performance of a spatial reinforced concrete frame with buckling‐restrained braces numerically. Results showed that the proposed method can enhance the accuracy of tests compared to conventional hybrid simulation, and keep computational efficiency in the meanwhile.

Wearable Device-Based Data Collection and Feature Analysis Method for Outdoor Sports

In recent years, with the rapid popularization of smart phones and wearable smart devices, it is no longer difficult to obtain a large number of human motion data related to people's heart rate and geographical location, which has spawned a series of running fitness applications, leading to the national running wave and promoting the rapid development of the sports industry. Based on the long short-term memory cyclic neural network, this paper processes, identifies, and analyzes the motion data collected by wearable devices. Through massive data training, a set of accurate auxiliary models of outdoor sports is obtained to help optimize and improve the effect of outdoor sports. The results show that the method proposed in this paper has a higher degree of sports action and feature recognition and can better assist in the completion of outdoor sports.

TMSCNet: A three-stage multi-branch self-correcting trait estimation network for RGB and depth images of lettuce

Growth traits, such as fresh weight, diameter, and leaf area, are pivotal indicators of growth status and the basis for the quality evaluation of lettuce. The time-consuming, laborious and inefficient method of manually measuring the traits of lettuce is still the mainstream. In this study, a three-stage multi-branch self-correcting trait estimation network (TMSCNet) for RGB and depth images of lettuce was proposed. The TMSCNet consisted of five models, of which two master models were used to preliminarily estimate the fresh weight (FW), dry weight (DW), height (H), diameter (D), and leaf area (LA) of lettuce, and three auxiliary models realized the automatic correction of the preliminary estimation results. To compare the performance, typical convolutional neural networks (CNNs) widely adopted in botany research were used. The results showed that the estimated values of the TMSCNet fitted the measurements well, with coefficient of determination (R2) values of 0.9514, 0.9696, 0.9129, 0.8481, and 0.9495, normalized root mean square error (NRMSE) values of 15.63, 11.80, 11.40, 10.18, and 14.65% and normalized mean squared error (NMSE) value of 0.0826, which was superior to compared methods. Compared with previous studies on the estimation of lettuce traits, the performance of the TMSCNet was still better. The proposed method not only fully considered the correlation between different traits and designed a novel self-correcting structure based on this but also studied more lettuce traits than previous studies. The results indicated that the TMSCNet is an effective method to estimate the lettuce traits and will be extended to the high-throughput situation. Code is available at https://github.com/lxsfight/TMSCNet.git.

Optimization Model and Settlement Mechanism of Electricity Market in Zhejiang Province under the Form of Diversified and Highly Resilient Grid

Taking Zhejiang power market as the research object, this article compares the spot market, medium and long-term market and auxiliary service market models in Zhejiang Province with reference to the theories and practical experiences related to the construction of power market at home and abroad. Combining the situation of Zhejiang Province, the network situation and the current situation of power market construction, a multi-period generation dispatch optimization model based on power contract is proposed, and a day-ahead market clearing model adapted to distributed energy participation is established. Based on the deep learning algorithm using simulation cases of multiple scenarios, the power market model under the multi-fusion high resilience grid form is designed to provide suggestions for the design of generation dispatch optimization model and settlement mechanism for different power market development stages.

Semi-supervised classifier guided by discriminator

Some machine learning applications do not allow for data augmentation or are applied to modalities where the augmentation is difficult to define. Our study aimed to develop a new method in semi-supervised learning (SSL) applicable to various modalities of data (images, sound, text), especially when augmentation is hard or impossible to define, i.e., medical images. Assuming that all samples, labeled and unlabeled, come from the same data distribution, we can say that labeled and unlabeled data sets used in the semi-supervised learning tasks are similar. Based on this observation, the data embeddings created by the classifier should also be similar for both sets. In our method, finding these embeddings is achieved based on two models—classifier and an auxiliary discriminator model, inspired by the Generative Adversarial Network (GAN) learning process. The classifier is trained to build embeddings for labeled and unlabeled datasets to cheat discriminator, which recognizes whether the embedding comes from a labeled or unlabeled dataset. The method was named the DGSSC from Discriminator Guided Semi-Supervised Classifier. The experimental research aimed evaluation of the proposed method on the classification task in combination with the teacher-student approach and comparison with other SSL methods. In most experiments, training the networks with the DGSSC method improves accuracy with the teacher-student approach. It does not deteriorate the accuracy of any experiment.

Early detection of colorectal cancer based on circular DNA and common clinical detection indicators.

BACKGROUNDColorectal cancer (CRC) is the third most common cancer worldwide, and it is the second leading cause of death from cancer in the world, accounting for approximately 9% of all cancer deaths. Early detection of CRC is urgently needed in clinical practice.AIMTo build a multi-parameter diagnostic model for early detection of CRC. METHODSTotal 59 colorectal polyps (CRP) groups, and 101 CRC patients (38 early-stage CRC and 63 advanced CRC) for model establishment. In addition, 30 CRP groups, and 62 CRC patients (30 early-stage CRC and 32 advanced CRC) were separately included to validate the model. 51 commonly used clinical detection indicators and the 4 extrachromosomal circular DNA markers NDUFB7, CAMK1D, PIK3CD and PSEN2 that we screened earlier. Four multi-parameter joint analysis methods: binary logistic regression analysis, discriminant analysis, classification tree and neural network to establish a multi-parameter joint diagnosis model. RESULTSNeural network included carcinoembryonic antigen (CEA), ischemia-modified albumin (IMA), sialic acid (SA), PIK3CD and lipoprotein a (LPa) was chosen as the optimal multi-parameter combined auxiliary diagnosis model to distinguish CRP and CRC group, when it differentiated 59 CRP and 101 CRC, its overall accuracy was 90.8%, its area under the curve (AUC) was 0.959 (0.934, 0.985), and the sensitivity and specificity were 91.5% and 82.2%, respectively. After validation, when distinguishing based on 30 CRP and 62 CRC patients, the AUC was 0.965 (0.930-1.000), and its sensitivity and specificity were 66.1% and 70.0%. When distinguishing based on 30 CRP and 32 early-stage CRC patients, the AUC was 0.960 (0.916-1.000), with a sensitivity and specificity of 87.5% and 90.0%, distinguishing based on 30 CRP and 30 advanced CRC patients, the AUC was 0.970 (0.936-1.000), with a sensitivity and specificity of 96.7% and 86.7%.CONCLUSIONWe built a multi-parameter neural network diagnostic model included CEA, IMA, SA, PIK3CD and LPa for early detection of CRC, compared to the conventional CEA, it showed significant improvement.

An Auxiliary Scoring Model for Patients with Acute Pulmonary Embolism Complicated with Atrial Fibrillation Was Established Based on Random Forests.

The purpose of this study was to explore the establishment of an auxiliary scoring model for patients with acute pulmonary embolism (APE) complicated with atrial fibrillation (AF) based on random forest (RF) and its application effect. A retrospective analysis was performed on the general data, underlying diseases, laboratory indicators, and cardiac indicators of 100 patients with APE admitted to our hospital from 2018 to 2021. The occurrence of atrial fibrillation in patients with pulmonary embolism was taken as a categorical variable, and the general data, underlying diseases, laboratory indicators, and cardiac indicators were taken as input variables. Then, the risk auxiliary scoring model for patients with APE complicated with AF was established based on RF and logistic regression. Finally, the accuracy, sensitivity, specificity, recall rate, accuracy, F1 value, and the receiver operator characteristic (ROC) curve were used to evaluate the predictive value of the models. After statistical analysis, the optimal node value was 3 and the optimal number of decision trees was 500 in the RF model. The importance of predictors in descending order were Hcy, diabetes mellitus, FT3 level, UA level, left atrial diameter, hypertension, and smoking history. The prediction accuracy of the RF model was 0.934, sensitivity 0.966, specificity 0.876, recall rate 0.9660, accuracy 0.934, and F1 value 0.950. The logistic regression model prediction accuracy was 0.816, sensitivity 0.915, specificity 0.125, recall rate 0.902, accuracy 0.811, and F1 value 0.896. The RF model and logistic regression prediction model AUC values were 0.984 and 0.883, respectively. From this, we conclude that the RF model was better than the logistic regression model in predicting AF in APE patients. So, the RF model had the clinical application value.

Compilation of a City-Level & Four-Digit Industry Code MRIO Table Based on Firm-Level Data

Scholars have attempted to compile various multi-region input-output (MRIO) tables for different countries. However, due to city-level data scarcity and methodology constraints, almost no MRIO table covers a large number of cities with more disaggregated sectors in countries with large economies, such as China. Based on two large-scale firm-level datasets, the China Annual Survey of Industrial Firms (CASIF) survey and the China Customs Data (CCD) database, from 2000 to 2013, this paper uses China as a case study and presents a new compilation method to construct an MRIO table covering 284 prefecture-level administrative cities and 334 four-digit sectors, which is by far the most comprehensive MRIO table with the largest number of cities and the most segmented industries in China. Unlike existing MRIO tables constructed based on provincial single-region IO (SRIO) tables, we use information along with various linear constraints implied by sector-level and firm-level statistics. This paper expands on the direct decomposition method by developing auxiliary econometric models necessary for estimations and consistency adjustment. In addition, a comparative analysis shows the reliability of our method, which guarantees better coherence and comparability with the MRIO officially published by the National Bureau of Statistics of China (NBS). Therefore, our proposed methodology provides the possibility of producing more disaggregated MRIO tables in other similar contexts.

A parallel based evolutionary algorithm with primary-auxiliary knowledge

The development of hybrid algorithms or the application of multiple strategies is one of the focal points for research on improving evolutionary algorithms. However, since most of the evolutionary equations of different algorithms can be transformed into each other, it is difficult to change the established properties of the given algorithm through a hybrid algorithm based on a mixture of evolutionary equations. In addition, multi-strategy methods tend to adopt the best strategy for the current local domain through greedy strategies in the solution process, which does not ensure validity in the global domain. Recently, Federated Learning has achieved remarkable results in machine learning, where the idea of model independence, parallelism and data sharing can essentially compensate for the weaknesses of hybrid and multi-strategy algorithms. Inspired by the idea of Federated Learning, this paper proposes an evolutionary algorithm named as parallel based Evolutionary Algorithm with primary-auxiliary knowledge. Specifically, a Spark-based primary-auxiliary knowledge model is developed, with different evolutionary algorithms used on each parallel sub-model. Then, an effective topological knowledge (individual) migration method is devised, which enables the primary knowledge model to learn the best knowledge from different auxiliary knowledge models through a topological structure. In this way, the best knowledge on the auxiliary knowledge models can be transferred to the primary knowledge model. Through a test conducted on the CEC2013 test set, it can be found out that the proposed algorithm clearly outperforms the 10 algorithms compared, which demonstrates the excellent performance of our proposed parallel based evolutionary algorithm with primary-auxiliary knowledge.

Profiles of achievement motivation and instructional dissent

ABSTRACT We integrated perspectives from achievement goal theory and expectancy-value theory to investigate how undergraduate students’ (N = 475) achievement motivation might influence their instructional dissent. A latent profile analysis of students’ achievement goals, performance self-efficacy, task value, and perceived cost revealed four distinct subgroups of students characterized by differences in their achievement motivation. Students between these latent profiles differed to some degree in their use of expressive and vengeful dissent but not rhetorical dissent. When examining instructor clarity as a triggering agent of dissent, lack of clarity was positively associated with all three types of instructional dissent; however, auxiliary moderation models revealed that latent profile membership did not moderate these effects. Our results suggest that although instructor clarity has similar effects on students’ instructional dissent—regardless of their latent profile membership—students still experience some differences in instructional dissent which can be explained by their achievement motivation profiles.