Max Operations Research Articles

CLPr_in_ML: Cleft Lip and Palate Reconstructed Features with Machine Learning

Background: Cleft lip and palate are two of the most common craniofacial congenital malformations in humans. It influences tens of millions of patients worldwide. The hazards of this disease are multifaceted, extending beyond the obvious facial malformation to encompass physiological functions, oral health, psychological well-being, and social aspects. Objective: The primary objective of our study is to demonstrate the importance of imaging in detecting cleft lip and palate. By observing the morphological and structural abnormalities involving the lip and palate through imaging methods, this study aims to establish imaging as the primary diagnostic approach for this disease. Methods: In this work, we proposed a novel model to analyze unilateral complete cleft lip and palate after velopharyngeal closure and non-left lip and palate patients from the Department of Stomatology of Xuzhou First People's Hospital, Conical Beam CT (CBCT) images in silicon. In order to demonstrate the generalization, the simulated dataset was constructed using the random disturbance factor, which is from the actual dataset. We extracted several raw features from CBCT images in detail. Then, we proposed a novel feature reconstruction method, including six types of reconstructed factors, to reconstruct the existing features. Then, the reconstructed features weretrained with machine learning algorithms. Finally, the testing and independent data model was utilized to analyze the performance of this work. Results: By comparing different operator features, the min operator, max operator, average operator, and all operators can achieve good performances in both the testing set and the independent set. result: none Conclusion: With the different operator features, the majority of classification models, including Gradient Boosting, Hist Gradient Boosting, Multilayer Perceptron, lightGBM, and broadened learning, classification algorithms can get the well-performances in the selected reconstructed feature operators.

Intelligent Traffic Control Decision-Making Based on Type-2 Fuzzy and Reinforcement Learning

Intelligent traffic control decision-making has long been a crucial issue for improving the efficiency and safety of the intelligent transportation system. The deficiencies of the Type-1 fuzzy traffic control system in dealing with uncertainty have led to a reduced ability to address traffic congestion. Therefore, this paper proposes a Type-2 fuzzy controller for a single intersection. Based on real-time traffic flow information, the green timing of each phase is dynamically determined to achieve the minimum average vehicle delay. Additionally, in traffic light control, various factors (such as vehicle delay and queue length) need to be balanced to define the appropriate reward. Improper reward design may fail to guide the Deep Q-Network algorithm to learn the optimal strategy. To address these issues, this paper proposes a deep reinforcement learning traffic control strategy combined with Type-2 fuzzy control. The output action of the Type-2 fuzzy control system replaces the action of selecting the maximum output Q-value of the target network in the DQN algorithm, reducing the error caused by the use of the max operation of the target network. This approach improves the online learning rate of the agent and increases the reward value of the signal control action. The simulation results using the Simulation of Urban MObility platform show that the traffic signal optimization control proposed in this paper has achieved significant improvement in traffic flow optimization and congestion alleviation, which can effectively improve the traffic efficiency in front of the signal light and improve the overall operation level of traffic flow.

INT-FUP: Intuitionistic Fuzzy Pooling

Convolutional Neural Networks (CNNs) are a kind of artificial neural network designed to extract features and find out patterns for tasks such as segmentation, recognizing objects, and drawing up classification. Within a CNNs architecture, pooling operations are used until the number of parameters and the computational complexity are reduced. Numerous papers have focused on investigating the impact of pooling on the performance of Convolutional Neural Networks (CNNs), leading to the development of various pooling models. Recently, a fuzzy pooling operation based on type-1 fuzzy sets was introduced to cope with the local imprecision of the feature maps. However, in fuzzy set theory, it is not always accurate to assume that the degree of non-membership of an element in a fuzzy set is simply the complement of the degree of membership. This is due to the potential existence of a hesitation degree, which implies a certain level of uncertainty. To overcome this limitation, intuitionistic fuzzy sets (IFS) were introduced to incorporate the concept of a degree of hesitation. In this paper, we introduce a novel pooling operation based on intuitionistic fuzzy sets to incorporate the degree of hesitation heretofore neglected by a fuzzy pooling operation based on classical fuzzy sets, and we investigate its performance in the context of image classification. Intuitionistic pooling is performed in four steps: bifuzzification (by the transformation of data through the use of membership and non-membership maps), first aggregation (through the transformation of the IFS into a standard fuzzy set, second aggregation (through the transformation and use of a sum operator), and the defuzzification of feature map neighborhoods by using a max operator. IFS pooling is used for the construction of an intuitionistic pooling layer that can be applied as a drop-in replacement for the current, fuzzy (type-1) and crisp, pooling layers of CNN architectures. Various experiments involving multiple datasets demonstrate that an IFS-based pooling can enhance the classification performance of a CNN. A benchmarking study reveals that this significantly outperforms even the most recent pooling models, especially in stochastic environments.

Variable parameters memory-type control charts for simultaneous monitoring of the mean and variability of multivariate multiple linear regression profiles

Variable parameters (VP) schemes are the most effective adaptive schemes in increasing control charts' sensitivity to detect small to moderate shift sizes. In this paper, we develop four VP adaptive memory-type control charts to monitor multivariate multiple linear regression profiles. All the proposed control charts are single-chart (single-statistic) control charts, two use a Max operator and two use an SS (squared sum) operator to create the final statistic. Moreover, two of the charts monitor the regression parameters, and the other two monitor the residuals. After developing the VP control charts, we developed a computer algorithm with which the charts' time-to-signal and run-length-based performances can be measured. Then, we perform extensive numerical analysis and simulation studies to evaluate the charts’ performance and the result shows significant improvements by using the VP schemes. Finally, we use real data from the national quality register for stroke care in Sweden, Riksstroke, to illustrate how the proposed control charts can be implemented in practice.

Efficient fuzzy multi-criteria decision-making for optimal college location selection: A comparative study of min–max fuzzy TOPSIS approach

Ranking fuzzy values is often essential in fuzzy multi-criteria decision-making (FMCDM) systems since it is established on the comparison of hazy data pairs, even though the comparison needs temporal complexity. Then to provide a fuzzy MCDM approach under min–max operations for avoiding the fuzzy comparison. By using fuzzy TOPSIS’s min and max operations, the suggested method produces two positive and negative ideal solutions of each alternative. Here, before discussing the effectiveness of the matrices between the alternatives, first to analyze the weighted strength and weakness indices from both positive and negative indices. The results of the method have been described using a straightforward case study of a proper location for creating a college. The best location can be identified using this method based on various criteria. The outcomes are also compared with the suggested method for its effectiveness. Additionally, this problem analyzes the fuzzy TOPSIS approach in an interval-valued number for greater efficiency.

Low Complexity Stopping Rule for Turbo Decoding: the Max-log Criterion

This paper presents a new stopping criterion for turbo decoding. It is based on the selection of the maximum log-alphas calculated by the log-MAP algorithm. The sum of these maximum alphas is compared with a threshold value. Then, a decision on the end of decoding is taken. Simulation results show that the max-log criterion offers the same performance as the sum-alpha and sum-log criteria, while maintaining the same complexity level. The max-log criterion uses only the max operator to select maximum alphas and a summation. Therefore, the proposed criterion is faster and offers lower complexity.

A study on the combination of functional connection features and Riemannian manifold in EEG emotion recognition.

Affective computing is the core for Human-computer interface (HCI) to be more intelligent, where electroencephalogram (EEG) based emotion recognition is one of the primary research orientations. Besides, in the field of brain-computer interface, Riemannian manifold is a highly robust and effective method. However, the symmetric positive definiteness (SPD) of the features limits its application. In the present work, we introduced the Laplace matrix to transform the functional connection features, i.e., phase locking value (PLV), Pearson correlation coefficient (PCC), spectral coherent (COH), and mutual information (MI), to into semi-positive, and the max operator to ensure the transformed feature be positive. Then the SPD network is employed to extract the deep spatial information and a fully connected layer is employed to validate the effectiveness of the extracted features. Particularly, the decision layer fusion strategy is utilized to achieve more accurate and stable recognition results, and the differences of classification performance of different feature combinations are studied. What's more, the optimal threshold value applied to the functional connection feature is also studied. The public emotional dataset, SEED, is adopted to test the proposed method with subject dependent cross-validation strategy. The result of average accuracies for the four features indicate that PCC outperform others three features. The proposed model achieve best accuracy of 91.05% for the fusion of PLV, PCC, and COH, followed by the fusion of all four features with the accuracy of 90.16%. The experimental results demonstrate that the optimal thresholds for the four functional connection features always kept relatively stable within a fixed interval. In conclusion, the experimental results demonstrated the effectiveness of the proposed method.

Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning.

The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is introduced to dynamically synthesis the subsequent inference information. To guide the formation of input membrane potentials and reduce the spike noise, we propose a global-local pooling (GLP) which combines the max and average pooling operations. Furthermore, the thresholds of the spiking neurons are dynamically adjusted based on semantic and temporal cues. Integrating the temporal and semantic information extracted by SNNs and Transformers are difficult due to the increased number of parameters in a straightforward bilinear model. To address this, we introduce a temporal-semantic Tucker fusion module, which achieves multi-scale fusion of SNN and Transformer outputs while maintaining full second-order interactions. Our experimental results demonstrate the effectiveness of the proposed approach in achieving state-of-the-art performance in three benchmark datasets. The harmonic mean (HM) improvement of VGGSound, UCF101 and ActivityNet are around 15.4%, 3.9%, and 14.9%, respectively.

Alternated Greedy-Step Deterministic Policy Gradient

The greedy-step Q-learning (GQL) can effectively accelerate the Q-value updating process. However, since it is an improvement version of Q-learning, the problem of Q-value overestimation also exists. Since there are in total two max operators used to iteratively calculate Q-value in GQL, many existing solutions to reduce the Q-value estimation bias are invalid for GQL. To address the issue, an alternated greedy-step update (AGU) framework that consists of two independent Q-value estimators is proposed in this study. In the proposed AGU framework, one estimator is to determine the time step that can maximize the estimated n-step return and the other estimator is to update the prior estimator using the target value calculated on the basis of the determined time step. The convergence of AGU framework is proved in theoretical. In addition, an alternated greedy-step deterministic policy gradient (AGDPG) that can be applied to continuous-action tasks is proposed by combining the AGU framework with deep deterministic policy gradient (DDPG). Experiments of AGDPG on continuous-action tasks of MuJoCo platform highlights its superior performance.

An improved IGDT approach for distributed generation hosting capacity evaluation in multi-feeders distribution system with soft open points

Unknown integrated locations caused by unpredictable consumers’ willingness and uncertainty in outputs induced by variable natural conditions are acknowledged challenges in the evaluation process of distributed generation (DG) hosting capacity (DGHC). For the former factor, this paper first proposes a novel assessment model to obtain the maximum feasible capacity no matter consumers in which locations have the possibility to stall DG. The decision variables of max operator and min operator are DG capacities and integrated locations respectively. Notably, unlike the previous works for one radial feeder, the interplay of DGHC in multi-feeders interconnected by tie lines and soft open points is also taken into consideration. After that, to combine uncertainties in integrated locations and outputs simultaneously, the above DGHC assessment model is further transformed into an improved information gap decision theory (IGDT) model with worst-case constraints for DG integrated locations. The specific solution procedure is also developed to solve this nonlinear IGDT model effectively. Case studies demonstrate that the evaluation results of DGHC based on this method always have the applicability and feasibility for any nodes in distribution system.

Stability evaluation of fault in hydrocarbon reservoir-based underground gas storage: A case study of W gas storage

Fault stability evaluation is crucial for ensuring safety of underground gas storage (UGS) reconstructed from depleted oil and gas reservoirs. To make assessment result more reasonable, a novel fault stability evaluation method is proposed, and four major faults in W gas storage are studied as a case to detailly describe this method. This method considers both shear rupture failure and frictional slip failure of fault based on Mohr-Coulomb criterion and Amonton’s law. In addition, dynamic variation in rock shear strength parameters under cyclic stress is understood and taken into account in fault stability evaluation by rock mechanics experiments. Meanwhile, specificity of fault friction coefficient in different UGSs is also considered in this method, and fault friction coefficient of W gas storage is determined by an empirical model. Fault stability evaluation results are quite disparate when different fault failure types are considered. For W gas storage, max operation pressure leading to fault failure is 62.10 MPa when shear rupture is regarded as fault failure type, and it reduce to 35.91 MPa when frictional slip is considered as fault failure type. Therefore, it is necessary to consider both two failure types, and further determine the key failure type in fault stability evaluation. Rock shear strength parameters vary with stress cycle, but the variation range is not significant in W gas storage. Rock cohesion shows a tendency that it fast declines first with stress cycles, then slow declines, and eventually tends to a constant. And variation in internal friction angle is contrary. Above both parameters orderly decrease by 3.08% and 8.75% after 53 cyclic stress cycles. The specificity of fault friction coefficient cannot be neglected in different UGSs. Otherwise, it could result in significant misestimate on fault stability of UGS. For W gas storage, fault friction coefficient is determined of 0.71 by empirical model, which is significant disparate to previous works. This work proposes an effective method which can help scholars and engineers to accurately evaluate fault stability in UGS.

Short-term electric load forecasting using particle swarm optimization-based convolutional neural network

Short-term electric load forecasting is essential for the operation of power systems and the power market, including economic dispatch, unit commitment, peak load shaving, load management and bidding strategy development. This paper presents a novel method that uses a hybrid convolutional neural network (CNN) that is cascaded with a fully-connected network, to conduct 24h-ahead electric load forecasting in power systems. Spearman’s rank-order correlation, which serves as input size information for the CNN, was used to measure the cross-correlation between two sets of observations (chronological loads) of time shifts or lags. Both max and average pooling operations were utilized to extract data features in concatenation while spatial and conventional dropouts were employed to avoid overfitting in the hybrid CNN. The proposed method used two loops to yield the optimal CNN. The outer loop optimizes the structure and hyperparameters (such as kernel size) of the hybrid CNN by a proposed method of enhanced elite-based particle swarm optimization (EEPSO) while the inner loop optimizes the parameters (such as values of a kernel) and weights in neural networks using the Adam optimizer. The EEPSO is based on the mean search and chaotic descending inertia weight. The proposed method was used to study the 2018 and 2019 hourly load data in Taiwan Power Company. Simulation results show that the proposed method outperforms the well-known ARIMA, Radial Basis Function Network, Support Vector Regression, Long Short-term Memory and their hybrid variants.

A Modified Hybrid Objective Model to Calculate the Weights of Cause and Effect Criteria in a System: DEMATEL and DEVELOPED SWARA (D-DS) Based Model

Abstract Criteria weighting is a widely used and also an important feature of multi criteria decision making problems specially in engineering, computer science and management investigations. In particular in many studies related to complex systems there would be usually two main groups of cause and effect criteria. In this research it is intended to make an hybrid objective model comprising DEMATEL and SWARA techniques to assign classified weights to the subgroup of cause and effect criteria. As a main goal, the proposed hybrid model in this presented paper can afford to assign greater values for criteria who belong to cause group. In this regard we apply the objective information which derived from the parameters of (R, equal to sum of direct and indirect influence of a criteria), (R/C, named as net influence power of a criteria) and (R-C, named as net effect of a criteria) related to the final total influence matrix T in DEMATEL methodology. The main contribution in this work lies in utilizing the SWARA methodology and making us of its revision where the relatively Comparative Importance Sj , applied in SWARA technique is reconfigured by some aggregation operators including max, Einstein and Hamacher operators for obtaining more uniformed weights of cause and effect criteria relatively to SWARA basic methodology. Finally results shows that the (R/C) and (R-C)would transfer more clear and refined data and numeric information achieving better and highly reliable weights of criteria categorized into two groups of cause and effect group.

Linguistic Complex Fuzzy Sets

Complex fuzzy sets (CFSs) are a suitable tool to manage spatial directional information which includes distance and direction. However, spatial directional information is given by linguistic values. It is very awkward for the CFS to describe this type of spatial directional information. To overcome this limitation, we first propose a novel concept called a linguistic complex fuzzy set (LCFS) to serve as an extension of the CFS. Then we put forward some basic operational laws for LCFSs. After that, we define three operators for LCFSs: the linguistic complex fuzzy weighted averaging (LCFWA) operator, the linguistic amplitude max (Amax) operator and the linguistic amplitude min (Amin) operator. In actual application, we use the LCFWA operator to deal with group decision making when the importance weights of experts are known. For the situation in which the weights of experts are unknown, we develop an Amax-Amin method for group decision making.

MODEL OF CYBER INCIDENT IDENTIFICATION BY SIEM FOR PROTECTION OF INFORMATION AND COMMUNICATION SYSTEMS

The article presents a model for identifying cyber incidents by a SIEM system that occur in the course of operation of information and communication systems (ICS). A list of tasks performed by the SIEM system in the ICS protection circuit and the mechanisms that form its basis, which, in turn, are components of the general process of correlation of events occurring in the ICS, is given. The methods of the correlation process aimed at removing, combining and linking data on events in the ICS with the establishment of its causality and priority are analyzed. It is concluded that the existing methods are ineffective in the context of incomplete and inaccurate information about cyber incidents. The tuple model for recognizing cyber incidents is analyzed and an improved model based on the theory of fuzzy sets and linguistic terms is proposed to eliminate its shortcomings. A new formulation of the problem of recognizing cyber incidents is proposed, which is reduced to their identification. The methods for solving it are analyzed and a number of their significant shortcomings are identified, which make it difficult to use them in practice. An approach to solving the formulated problem of identifying cyber incidents by a SIEM system is proposed on the basis of forming a fuzzy knowledge base of the SIEM system about their features based on the collection of expert information and its further processing by applying the theory of fuzzy sets. The basic principles that should be used when developing a mathematical model for identifying cyber incidents by a SIEM system are formulated. A model of a fuzzy knowledge base of cyber incidents is proposed in the form of a multidimensional table with the features of cyber incidents represented by linguistic terms and classes that correspond to them. A representation of the fuzzy knowledge base (matrix) in the form of a system of fuzzy rules of the "IF-THEN" type is presented, and on their basis, by applying the min and max operations, a model for identifying cyber incidents by a SIEM system is proposed. It is concluded that it is expedient to use the model presented in the paper to protect information and communication systems in the conditions of incomplete and inaccurate information about cyber incidents arising in the course of their operation.

Some equations to identify the threshold value in the DEMATEL method

DEMATEL technique is a graphical representation method to deal with complex systems. The final analyzed cause and effect categorization would be fundamentally dependent on the threshold value setting. This research is intended to present some mathematical models for calculating the threshold value in the DEMATEL method. The min(max) operator has been intentionally used for considering three equations to identify the threshold value. Additionally, the proposed mathematical equations are gradually developed to gain more useful data to yield a threshold value as well. Particularly, the expert’s initial scoring for building the primary matrix would also be applied in one equation. Results show eliciting an expert’s opinions regarding the value of a threshold value determination leads to setting relatively high thresholds. But, there would be an equation which takes advantage of more data derived from the total influence matrix T. Moreover, a span of different threshold values is gained by making use of the Hamacher t-conorms operator which especially would cause better complexity management of the final total matrix T based on expert’s opinions. As a contribution to this research, threshold value determination is developed mathematically by making use of the direct data gained by the total matrix T. Besides combining data derived from total matrix T, the initial influence direct matrix given by experts, a simpler aggregating procedure and no need for statistical information compared to special Lenth’s method hints at this research’s novelty as well.

Methods for solving balanced fuzzy systems of equation

Human decision-making is an essential direction of current research. Fuzzy sets and relations have been used to model human behavior, reasoning, and decision-making over the years. Since social science research shows that omitting or zeroing out negative information does not fully describe human behavior and decision-making, the concept of balanced sets and relations was developed in response to this problem. Balanced sets and relations are mathematical concepts that support both positive and negative data analysis. Balanced sets of equations are considered to find relationships between different sets. In this article, the idea of balanced systems of equations is presented. The paper discusses the existence and how to determine their set of solutions. A method for solving balanced systems of equations with balanced MAX and MIN operations is given.

A New Similarity Measure of Fuzzy Signatures with a Case Study Based on the Statistical Evaluation of Questionnaires Comparing the Influential Factors of Hungarian and Lithuanian Employee Engagement

Similarity between two fuzzy values, sets, etc., may be defined in various ways. The authors here attempt introducing a general similarity measure based on the direct extension of the Boolean minimal form of equivalence operation. It is further extended to hierarchically structured multicomponent fuzzy signatures. Two versions of this measure, one based on the classic min–max operations and one based on the strictly monotonic algebraic norms, are proposed for practical application. A real example from management science is chosen, namely the comparison of employee attitudes in two different populations. This example has application possibilities in the evaluation and analysis of employee behaviour in companies as, due to the complex aspects in analysing multifaceted behavioural paradigms in organizational management, it is difficult for companies to make reliable decisions in creating processes for better social interactions between employees. In the paper, the authors go through the steps of building a model for exploring a set of different features, where a statistical pre-processing step enables the identification of the interdependency and thus the setup of the fuzzy signature structure suitable to describe the partially redundant answers given to a standard questionnaire and the comparison of them with help of the (pair of the) new similarity measures. As a side result in management science, by using an internationally applied standard questionnaire for exploring the factors of employee engagement and using a sample of data obtained from Hungarian and Lithuanian firms, it was found that responses in Hungary and Lithuania were partially different, and the employee attitude was thus in general different although in some questions an unambiguous similarity could be also discovered.

A new medical image enhancement algorithm using adaptive parameters

AbstractThe quality of medical images plays a vital role in many image processing applications such as image segmentation, feature extraction, image classification, image recognition, and image fusion. Some of the common problems with Medical images are noise, blur, or low contrast. According to our observations, current image enhancement algorithms only focus on solving individual problems such as gray level adjustment, noise reduction, or sharpness enhancement. This paper proposes a novel algorithm to solve problems on images simultaneously. First, we propose an image decomposition algorithm. This algorithm allows decomposing the image into three components: structure (IS), texture (IT), and noise (IN). Second, the structural component (IS) is enhanced by the contrast‐limited adaptive histogram equalization method to obtain ICLAHE. We use the structure tensor salient detection operator and the Laplace edge detection operator to add structural and texture features. These operators are applied to the ICLAHE and IT components to obtain the ISTS and ILED components, respectively. The IT and ILED components are used to generate the enhanced component (called ) by using the Max operator. Third, the Marine predators algorithm is used to find the optimal parameters β1, β2, β3, and β4 corresponding to ICLAHE, ISTS, , and IN. Finally, the enhanced image is made up of the sum of the ICLAHE, ISTS, , and IN images multiplied by the optimal parameters β1, β2, β3, and β4, respectively. Six state‐of‐the‐art image enhancement approaches, seven medical image fusion algorithms, and six image quality metrics have been utilized to verify the proposed approach's effectiveness. The experimental results show that the proposed method significantly improves the quality of the input medical images as well as significantly improves the efficiency of current medical image synthesis algorithms.

MulSimNet: A multi-branch sub-interest matching network for personalized recommendation

Personalized recommendation serves as an indispensable functionality in many online services, where the key is to model the user’s preference based on past user-item interactions. Many well-known models learn a latent vector for each user and each item. Nevertheless, a single latent vector might not be able to well represent a user’s multifaceted interests revealed by the wide variety of items consumed by him/her. In this paper, we present a flexible framework named Multi-branch Sub-interest matching Network (MulSimNet) for personalized recommendation. Each user is explicitly represented by multiple sub-interest vectors as well as a general interest vector, and an item is matched against these vectors through different branches, where each branch is realized by appropriate neural networks. The compatibility scores output by multiple sub-interest matching branches are first aggregated via the max operator, which is then fused with the output of the general interest matching branch to estimate the user’s affinity with the item. A comprehensive set of experiments on benchmark datasets demonstrate the effectiveness of the proposed framework in fully capturing the user’s multifaceted interests and yielding better top-N recommendations.