Input Membership Research Articles

Application of adaptive neuro-fuzzy simulation system for elucidation of water absorption process of lentil seeds

Adaptive neuro-fuzzy simulation of engineering phenomena can be a supportive manner for integrated realization of compound trends of involved parameters. This paper deals with applying of adaptive neuro-fuzzy simulation system for elucidation of hydration kinetics of lentil seeds in water absorption process with thermic and ultrasonication approaches. The simulation system was implemented based on various types and numbers of input membership functions, defuzzification methods, types of output membership functions, and numbers of training cycles. Promising performance of the simulation system guaranteed its reliability for elucidation of hydration kinetics on the basis of numeral variables of soaking period and temperature (20, 30, 40, 50 and 60 °C), and nominal variable of soaking approach (thermic and ultrasonication (25 kHz, 360 W)). The simulation results elucidated that applying both approaches of thermic and ultrasonication (thermo-ultrasonication approach) was more effective than individual approach of thermic and ultrasonication in order to proliferate water absorption into the seeds. However, contributory influence of the ultrasonication on water absorption was less apparent at higher soaking temperatures and it was more dominant, when soaking period increased. It can be asserted that adaptive neuro-fuzzy simulation results obtained in this study can be practically utilized for augmentation of dehulling efficiency in industrial processing of lentil seeds.

Flight Controller Design for Altitude Control of a Quadcopter using PID and Fuzzy Methods

A quadcopter can be manually controlled or can be autonomous. Therefore, a control system is needed to support the quadcopter's movement. PID and fuzzy control are used in this research to adjust the quadcopter's altitude position. The control system proposed in this research is to keep the quadcopter at a certain altitude. The control system design uses a PID controller, where the control parameters are obtained using the Ziegler-Nichols 2 tuning method. Ziegler-Nichols 2 tuning method is used to obtain the parameters Kp, Ti, and Td. PID control tuning becomes a reference for fuzzy control design in determining input and output membership functions and the rules. Also, in this study, the flight controller board design is proposed. The experiment results show that the PID control has a faster rise time of 0.2 seconds, a better maximum overshoot of 1.56%, a quicker settling time of 1.69 seconds, and a steady-state error of 0% compared to the fuzzy control. The result shows that the use of PID control is more suitable for proposed quadcopter plants because it requires a fast output response.

Critical rare earth metal adsorption onto expanded vermiculite: Accurate modeling through response surface methodology and machine learning techniques

The circular economy of rare earth metals (REM), such as dysprosium, is essential for a sustainable future in clean energy and high-tech fields. Adsorption has gained attention to recover and reintegrate REM into the productive chain; however, accurate modeling of adsorptive processes still needs to be addressed, which delays further scale-up studies. Thus, this paper studied the adsorption of Dy on expanded vermiculite and applied novel empirical methods, such as artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS), and the classical response surface methodology (RSM) for modeling of dysprosium recovery as a function of adsorbent size, mass, and pH of the solution, variables often ignored in the mathematical modeling of adsorption. In our work, the effect of each operational parameter on Dy removal efficiency was examined by the RSM approach, in which only the adsorbent dosage and pH were the significant factors. So, ANFIS with two input membership functions (Gaussian type) was the most accurate procedure to predict and model the dysprosium removal efficiency (R2 = 0.99681). Also, vermiculite removed dysprosium with high efficiency (99.2%) under the best experimental conditions, at pH around 3.5 and adsorbent mass of 0.64 g, indicating an effective process optimization. The loaded vermiculite, after the adsorption, was characterized by textural and thermal properties that confirmed the stability of the material. Thus, according to basic operational parameters, accurate modeling of the Dy adsorption on expanded vermiculite (a low-cost, available, and non-toxic material) can improve adsorption technology's maturity to reconcentrate and recover rare earth metals.

A sustainable biochar-based shape stable composite phase change material for thermal management of a lithium-ion battery system and hybrid neural network modeling for heat flow prediction

Electric vehicles are gaining global popularity lately, and along with it, efficient battery thermal management systems (BTMS) are also gaining traction amongst the research community. Phase change material (PCM) based BTMS can be an attractive solution due to its high energy density and isothermal energy exchange. However, pure PCM has some drawbacks like low thermal conductivity, volume expansion, and leakage during phase change. A shape stable composite PCM (SSCPCM) resolves these drawbacks but is an expensive solution due to the high cost of conventional supporting materials. Biochar (BC) based SSCPCM developed in this study can be a cheap and sustainable solution for BTMS. The characterization studies are carried out for combination of pure PCM (Myristyl Alcohol) and biochar at various loadings of 6 %, 12 %, 18 %, and 24 % by weight, using Fourier transform infrared analysis (FT-IR), X-ray diffraction (XRD) analysis, scanning electron microscopy (SEM), particle size analysis (PSA), differential scanning calorimetry (DSC), and thermogravimetric analysis (TGA). The shape stability studies reveal that the PCM with minimum of 24 % biochar (PCM-BC24) is shape stable. The thermal conductivities and effusivities of pure and shape-stable composite PCMs are also studied. Enhancement in thermal conductivity of PCM-BC24 is studied with the addition of multi-walled carbon nanotubes (MWCNT) in 0.5 % and 1 % concentrations. FT-IR and XRD results reveal that the interaction of biochar and MWCNT with pure PCM is purely physical and chemically stable. The degree of supercooling is reduced by 19.26 %, 23.49 %, and 25.17 % for PCM-BC24 with 1 % MWCNT compared to pure PCM at a heating rate of 5.0, 7.5, and 10 °C/min, respectively. Thermal conductivity and effusivity of PCM-BC24 with 1 % MWCNT are 458.72 % and 146.25 % higher than the pure PCM, respectively. The TGA results reveal that PCMs thermal stability is not adversely affected by the addition of BC & MWCNT. Furthermore, an ANFIS model is developed to predict the heat flow (mW/mg) values of PCM samples and found that the generalized bell-shaped input and linear output membership function is best suitable with a coefficient of determination (R2) of 0.971.

Performance Evaluation of the Impact of Clustering Methods and Parameters on Adaptive Neuro-Fuzzy Inference System Models for Electricity Consumption Prediction during COVID-19

Increasing economic and population growth has led to a rise in electricity consumption. Consequently, electrical utility firms must have a proper energy management strategy in place to improve citizens’ quality of life and ensure an organization’s seamless operation, particularly amid unanticipated circumstances such as coronavirus disease (COVID-19). There is a growing interest in the application of artificial intelligence models to electricity prediction during the COVID-19 pandemic, but the impacts of clustering methods and parameter selection have not been explored. Consequently, this study investigates the impacts of clustering techniques and different significant parameters of the adaptive neuro-fuzzy inference systems (ANFIS) model for predicting electricity consumption during the COVID-19 pandemic using districts of Lagos, Nigeria as a case study. The energy prediction of the dataset was examined in relation to three clustering techniques: grid partitioning (GP), subtractive clustering (SC), fuzzy c-means (FCM), and other key parameters such as clustering radius (CR), input and output membership functions, and the number of clusters. Using renowned statistical metrics, the best sub-models for each clustering technique were selected. The outcome showed that the ANFIS-based FCM technique produced the best results with five clusters, with the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Variation (RCoV), Coefficient of Variation of the Root Mean Square Error (CVRMSE), and Mean Absolute Percentage Error (MAPE) being 1137.6024, 898.5070, 0.0586, 11.5727, and 9.3122, respectively. The FCM clustering technique is recommended for usage in ANFIS models that employ similar time series data due to its accuracy and speed.

Multiobjective Evolution of the Explainable Fuzzy Rough Neural Network With Gene Expression Programming

The fuzzy logic-based neural network usually forms fuzzy rules via multiplying the input membership degrees, which lacks expressiveness and flexibility. In this article, a novel neural network model is designed by integrating the gene expression programming into the interval type-2 fuzzy rough neural network, aiming to generate fuzzy rules with more expressiveness utilizing various logical operators. The network training is regarded as a multiobjective optimization problem through simultaneously considering network precision, explainability, and generalization. Specifically, the network complexity can be minimized to generate concise and few fuzzy rules for improving the network explainability. Inspired by the extreme learning machine and the broad learning system, an enhanced distributed parallel multiobjective evolutionary algorithm is proposed. This evolutionary algorithm can flexibly explore the forms of fuzzy rules, and the weight refinement of the final layer can significantly improve precision and convergence by solving the pseudoinverse. Experimental results show that the proposed multiobjective evolutionary network framework is superior in both effectiveness and explainability.

Multi-characteristic optimization and modeling analysis of electrocoagulation treatment of abattoir wastewater using iron electrode pairs

Multi-characteristic optimization and modeling analysis of electrocoagulation (EC) treatment of abattoir wastewater (AWW) using iron‑iron electrodes are reported. Response Surface Methodology (RSM) and Artificial Intelligent (AI) modeling tools viz. Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used for the modeling while the numerical method of RSM and RSM-based Genetic Algorithm (RSM-GA) were used to optimize the response variable. The independent variables were pH, current intensity, electrolysis time, settling time, and temperature while the dependent variable was percentage turbidity removal. Based on high determination coefficient (R2) and low standard deviation (SD) values, the quadratic model was selected from the ANOVA of the RSM model. For the ANN model, the number of neurons were varied between 2 and 10 but based on low MSE and high R2 values, 10 was selected as the optimum number of neurons. The ANFIS network used the triangular input membership function (trimf) with 100 epochs. The three models depicted linear adequacy with respective R2 values of 0.9978, 0.9995, and 0.8285 for RSM, ANFIS, and ANN respectively. However, the performance error indices indicated that the prediction accuracy of the three models followed the order — ANFIS > ANN > RSM. Further, the validated optimization results produced 94.74 % and 97.42 % turbidity removal for the RSM and RSM-GA optimization methods respectively. This proved that RSM, ANN, and ANFIS can reliably be used to model the EC treatment of AWW using FeFe electrodes; while the response variable can successfully be optimized by RSM and RSM-GA methods.

Load Management and Optimal Sizing of Special-Purpose Microgrids Using Two Stage PSO-Fuzzy Based Hybrid Approach

The sizing of microgrids depends on the type of load and its operational hours. The significance of understanding the load operational characteristics in special purpose islanded microgrids is much needed for economic system sizing. The load operation of special-purpose microgrids often consumes high power for a short duration and remains idle most of the time, thus reducing the load factor. The inclusion of such loads in microgrid sizing causes huge capital costs making islanded microgrids an unfeasible solution. The islanded microgrid under study is an agricultural microgrid in a village having a small Crab Processing Plant (CPP) and a Domestic Sector (DS). The CPP constitutes the major power consumption. The community has a unique load consumption trend that is dependent on the highly uncertain parameter of availability of the crabs. Interestingly, crab availability is an independent parameter and cannot be accurately scheduled. The existing system sizing of the microgrid is performed based on the conventional methods that consider the CPP for full-day operation. However, the microgrid sources, especially the storage system may be reflected as oversized if the crab processing plants do not operate for several days due to the uncertain behavior of CPP causing enormous power wastage. In this paper, an integrated fixed and operational mode strategy for uncertain heavy loads is formulated. The proposed algorithm is based on the optimal sizing methodology aided by the load scheduling control strategy. The Particle Swarm Optimization technique is used for the optimal sizing integrated with the fuzzy logic controller to manage the available load. The membership functions are available excess power and the state of the charge of storage that defines the operational conditions for CPP. Based on input membership functions, the fuzzy controller decides on power dispatch in DS or CPP, keeping considerable SoC available for night hours. The simulation result shows that the time-dependent fuzzy controller approach manages to provide power to both sectors under optimal sizing while reducing the overall cost by 24% less than the existing microgrid.

Construction of a Chlorophyll Content Prediction Model for Predicting Chlorophyll Content in the Pericarp of Korla Fragrant Pears during the Storage Period

A chlorophyll content prediction model for predicting chlorophyll content in the pericarp of Korla fragrant pears was constructed based on harvest maturity and storage time. This model predicts chlorophyll content in the pericarp of fragrant pears after storage by using the error backpropagation neural network (BPNN), generalized regression neural network (GRNN) and adaptive neural fuzzy inference system (ANFIS). The results demonstrate that chlorophyll content in the pericarp of fragrant pears decreased gradually as the harvest time lengthened. The chlorophyll content in the pericarp of fragrant pears with different maturity levels at harvest decreased continuously with the increase in storage time. According to a comparison of the prediction performances of the BPNN and ANFIS models, it was discovered that the trained GRNN and ANFIS models could predict chlorophyll content in the pericarp of fragrant pears. The ANFIS model showed the best prediction performances when the input membership functions were gasuss2mf (RMSE = 0.006; R2 = 0.993), dsigmf (RMSE = 0.007; R2 = 0.992) and psigmf (RMSE = 0.007; R2 = 0.992). The findings of this study can serve as references for determining the delivery quality and timing of Korla fragrant pears.

Reversible data hiding scheme exploiting center folding with fuzzy weight strategy

Despite the fact that image interpolation is a well-established strategy in image processing, and many scholars have outlined numerous data hiding schemes based on it but current demand still has flaws. In this paper, a novel efficient reversible data hiding scheme has been developed after performing image interpolation by exploiting center folding with fuzzy weight strategy (FWS). The interpolated pixel values are obtained by considering the fuzzy weight of each pair of pixels in an selected image block. The fuzzy membership values of each input pixel pair has been regarded the range between minimum and maximum value of that block. The fuzzy output function feed into the input membership value and then the strength of the fuzzy rule has been calculated using Max–Min composite principle. After that, based on the strength of fuzzy rule, interpolated pixel value are computed from fuzzy output function through defuzzification process. In fact, fuzzy weight based interpolation algorithms produce virtual pixel, which is better than existing interpolation schemes. Then data hiding operation has been performed in each interpolated pixel through center folding strategy comparing with signal of secret data. If the signal of the secret data is different from the interpolated pixel, then the proposed scheme reverses the folded value to match the secret data for decreasing the image distortion between the interpolated image and the stego-image. At the receiver’s end, the secret data can be obtained based on the difference of the results of these interpolated values with center folding strategy (CFS). The proposed FWS achieved visual quality measured by PSNR 29.99 (dB) which is higher than existing image interpolations schemes. Furthermore, after embedding secret data through CFS we achieve PSNR0 33.40 (dB), PSNR1 33.45(dB) and PSNR2 48.012 (dB) for k=2 with embedding capacity 1.48 bpp which is more higher than state of the other methods. The experimental outcomes indicate that the proposed model is worthy to encode huge amount of secret bits with a enhanced visible quality, which can be anticipated by examining with existing ideas. The conveyed phenomenon emphasized some effective noble characteristics in the research area of hidden data communication for authentication, tampered detection without which today’s high-tech life stunts. This method gains exceptionally from many aspects of private, public or government sectors including education, economy, military and medical application.

Нечеткая логика и интеллектуальное управление инженерными системами зданий

Energy consumption factors in the systems of cooling, heating, air conditioning and lighting in a building have a significant impact on the energy costs. Intelligent energy control methods help modernize the engineering systems of buildings, while using artificial neural networks and fuzzy logic for minimizing energy consumption is espe-cially effective in the operation of buildings. To control energy consumption there was proposed the Mamdani fuzzy inference system, selected membership functions of Gaussian, triangular and trapezoidal shapes in the course of the research, implemented the types and functions of inputs and outputs for engineering systems control subsystems in software. According to the input and output parameters, the following systems were designed: lighting, smart window, HVAC; fuzzy inference tables were built, graphical data analysis was performed. The proposed control solutions for the implementation of fuzzy rules based on linguistic variables make it possible to adapt the building management system to environmental conditions and prevent excessive energy consumption. The study substantiates the choice of energy-consuming parts of the building; when forming control actions, fuzzy logic rules are applied in functional ranges. The fuzzy inference system was shown to generate the solutions in accordance with changing input data, integrated control is implemented, the responses of lighting, heating, ventilation and air conditioning systems are analyzed depending on the input membership function. It is proposed to control the intensity of ambient light using motion sensors, including optical ones. It is shown that the results obtained make it possible to achieve a reduction in lighting energy consumption by 15 - 25%, maximum use of external light, ensuring a comfortable temperature regime, and also lead to implementing the coordinated and integrated control functions

Trust identification through cognitive correlates with emphasizing attention in cloud robotics

Attention and Trust remain the crux of robotic sensory perception when associated with cloud robotics. It involves tasks that compete for attention from several stimuli taken by the robot itself upon its selective attention mode, focuses its attention on the task with higher precedence, and filters out the rest to be performed later. The robot could unload storage-extensive and computation extensive jobs towards the cloud while keeping trust establishment in control. Factors leading to these robots' availability, confidentiality, data protection, and isolation security trigger attention. Trust involving suppliers and users is intended to attain safety measures that endorse various cloud suppliers' status and accessible services. It takes several input stimuli from the robot, i.e., confidence, experience, and emotion, and gives output as trust level to pay attention during social interactions among robots. Input parameters are mapped into fuzzy sets, taking a range of input and output membership functions. The fuzzifier and defuzzifier are designed according to the proposed scheme. The developed system, named Trust Annotator, is tested and analyzed using MATLAB R2021a. Mamdani model is conferred, which yielded some unusual yet promising outcomes. These outcomes show conformity between the designed and simulated systems.

Fuzzy logic modelling in drilling operation

In this research, work various machining parameters can be analyzed with the help of fuzzy logic model. In industry, mostly drilling machines will be used for making various types of holes. It has its importance because of its complexity and economic in nature. In drilling operation various machining parameters like spindle speed, feed rate, depth of cut analyzed with help of Design of experiments (DOE) concept along with the fuzzy logic. CNC Milling machine is used to perform drilling operation on phosphor bronze plate of dimensions 98 mm × 98 mm × 8 mm. Speed of Spindle(SS), depth of cut(DOC) and feed rate(FR) are the selected machining parameters and the responses are Surface roughness(SR), Material removal rate(MRR). Fuzzy logic model is developed based on universe portioning, rules formation, rules combination, fuzzy relation and relationship between input and output membership function. As an experimental result, it is known that high MRR will occurs when increasing of SS and DOC.SR increases with rise in speed and cutting depth. The predicted value using fuzzy logic is close enough to experimental value.

Soil Nutrient Detection and Recommendation Using IoT and Fuzzy Logic

Precision agriculture is a modern farming practice that involves the usage of Internet of Things (IoT) to provide an intelligent farm management system. One of the important aspects in agriculture is the analysis of soil nutrients and balancing these inputs are essential for proper crop growth. The crop productivity and the soil fertility can be improved with effective nutrient management and precise application of fertilizers. This can be done by identifying the deficient nutrients with the help of an IoT system. As traditional approach is time consuming, an IoT-enabled system is developed using the colorimetry principle which analyzes the amount of nutrients present in the soil and a fuzzy expert system is designed to recommend the quantity of fertilizers to be added in the soil. A set of 27 IF-THEN rules are framed using the Mamdani inference system by relating the input and output membership functions based on the linguistic variable for fertilizer recommendation. The experiments are conducted using MATLAB for different ranges of Nitrogen (N), Phosphorous (P) and Potassium (K). The NPK data retrieved by the system is sent to the ThingSpeak cloud and displayed on a mobile application that assists the farmers to know the nutrient information of their field. This system delivers the required nutrient information to farmers which results in efficient green farming.

Partial Discharge Localization in Oil through Acoustic Emission Technique Utilizing Fuzzy Logic

This study presents an examination of partial discharge (PD) localization in oil based on acoustic emission technique utilizing fuzzy logic. First, the PD measurement and localization systems are developed. In total, 2 coordinates of needle-plane electrodes that represent the PD location and 336 acoustic emission sensor (AES) coordinates are examined. The electrical PD is measured through an impedance matching circuit (IMC). The acoustic PD is acquired through AES and its signal is boosted by a preamplifier gain unit. The acoustic and electrical PDs are collected once the voltage reaches 30 kV. The data are first preprocessed by discrete wavelet transform (DWT) whereby it will be further analyzed by time of arrival (TOA), fuzzy logic Mamdani (FLM), and fuzzy logic Takagi–Sugeno (FLTS) methods. The arrival of time and distance between PD and AES are calculated based on TOA to find the PD location. Next, TOA and distance to PD location are used to define the input and output membership functions for FLM and FLTS to determine the PD location. It is found that FLTS has a great potential to be used for localization of the PD in oil whereby it has the lowest errors between actual PD location and AES. The performance of FLM and TOA is inferior to FLTS whereby the errors between actual PD location and AES are quite high for both PD locations.

Prediction of Diabetes Empowered With Fused Machine Learning

In the medical field, it is essential to predict diseases early to prevent them. Diabetes is one of the most dangerous diseases all over the world. In modern lifestyles, sugar and fat are typically present in our dietary habits, which have increased the risk of diabetes. To predict the disease, it is extremely important to understand its symptoms. Currently, machine-learning (ML) algorithms are valuable for disease detection. This article presents a model using a fused machine learning approach for diabetes prediction. The conceptual framework consists of two types of models: Support Vector Machine (SVM) and Artificial Neural Network (ANN) models. These models analyze the dataset to determine whether a diabetes diagnosis is positive or negative. The dataset used in this research is divided into training data and testing data with a ratio of 70:30 respectively. The output of these models becomes the input membership function for the fuzzy model, whereas the fuzzy logic finally determines whether a diabetes diagnosis is positive or negative. A cloud storage system stores the fused models for future use. Based on the patient’s real-time medical record, the fused model predicts whether the patient is diabetic or not. The proposed fused ML model has a prediction accuracy of 94.87, which is higher than the previously published methods.

Optimization of Fuzzy Logic Based Virtual Pilot for Wargaming

This paper deals with the design of an autopilot based on a set of fuzzy controllers. The model of the aircraft that the autopilot controls is defined as a model with 6 degrees of freedom, where the inputs to this model are the settings of the engine thrust (DX), rudder rotation (Dl) and elevators (Dm and Dn). The fuzzy controllers are of the Mamdani type, where the set of parameters defining the controller allow the derivation of membership functions of the input variables and membership functions of the output variables. The parameters of fuzzy controllers are determined by the optimization process. For the purpose of optimization, a fitness function is defined, which derives the simulation parameters from its parameter (vector), and the simulation subsequently performed and evaluated determines whether it is a feasible solution in addition the value of this solution. By this optimization process, the sub-optimal solution is found and is then used to define the settings of the fuzzy controllers and, therefore, the autopilot. This paper contains a description of each step of the solution of the described problem, and with the help of the obtained results, it is determined that the presented procedure allows us to find an autopilot capable of controlling the defined model of the aircraft. In addition, there is a brief description regarding the misconceptions explored during the development of the experiment.

Innovation Quinary and n‐Value toward Fuzzy Logic QCA Cell Design

AbstractQuantum Cellular automata (QCA) is a technology developed to replace complementary metal‐oxide‐semiconductor (CMOS) technology that faces increasing challenges due to the miniaturization of CMOS dimensions. The use of multi‐valued QCA is of interest because of its proximity to fuzzy logic, and lower power consumption. A two‐layer quinary system is proposed and the basic logic gates are examined and simulated to confirm the correct performance of the proposed cell. The proposed cell employs two layers because the presence of more than two particles per layer destabilizes the design of logic gates. The proposed Quinary QCA(QuQCA) cell can be implemented in one layer using input and output derives. Simple relationships are proposed to calculate the polarization values and the number and type of layers, so complex quantum computations can be avoided. The quantum power consumption and the proposed cell power consumption of the quinary system are calculated and compared. Finally, we present n‐valued cells without using quantum computation, and these cells are examined in terms of the number of particles, polarization value, and cell structure. The n‐level cell can be investigated more easily than other technologies due to its proximity to fuzzy logic and the design of the input, output, and fuzzy membership function.

Multi-speed gearbox design and shifting control optimization to minimize fuel consumption, exhaust emissions and drivetrain mechanical losses

Internal combustion engine vehicles (ICEVs) still represent a major fraction of the global vehicle market and enhancements of conventional vehicle powertrain design have been considered a viable large-scale alternative to reach short-term sustainable goals focused on the reduction of air pollutant emissions and fuel consumption. Thus, the purpose of this paper is to employ a multi-objective optimization for the ICEV drivetrain design and gear shifting control aiming at the minimization of fuel consumption, exhaust emissions and gearbox power losses. The optimization problem is solved by the Interactive Adaptive-Weight Genetic Algorithm (i-AWGA) and comprises different design variables of the multi-speed transmission and differential system, considering constructive constraints. The i-AWGA procedure also optimizes the fuzzy logic shifting controller by defining its input and output membership functions, fuzzy rules and respective weights. The vehicle model is evaluated under a combined driving cycle, therefore robust powertrain configurations can be obtained by the optimization process. The best trade-off solution results in the reduction of gas emissions in 2.32% HC, 3.44% CO and 23.78% NOx, along with the 15.6% fuel savings, facing the standard vehicle.

Retraction Note to: Sensitivity of mountain landslide based on Markov model and aerobic training management

In this paper, we will use MATLAB to create a Markov model, determine the input and output membership functions of the study area, and import the data of the study area into the model. The ROC method is used to prove the accuracy of the sensitivity distribution map of mountain landslide disaster and the feasibility of the model in the sensitivity assessment of mountain landslide. It also shows the reliability and applicability of the selected factors. Based on GIS technology, the influencing factors of sensitivity coefficient of landslides in mountainous areas can be extracted. According to the spatial distribution characteristics of landslides, six influencing factors of landslides and their spatial distribution relationships are analyzed: height, slope, geological lithology, terrain curvature, terrain humidity index, and runoff intensity index. Training management combined with aerobic exercise is helpful to improve people’s body shape. The effect of “resistance training + aerobic exercise” training method adopted by experimental group 1 on body shape is the most significant. The arm circumference of the male experimental group increased, while that of the female experimental group decreased. In the training management, different combination methods of resistance training and aerobic exercise have no significant effect on the improvement of the muscle strength of the subjects after the experiment. By analyzing and comparing the changes of cardiopulmonary function indexes of the subjects before and after training, this paper expounds the training effect of blood flow restriction under different pressures combined with low-intensity aerobic exercise on cardiopulmonary function. In this paper, through the study of the Markov model and mountain landslide sensitivity, it is applied to aerobic training management, which promotes the better improvement of people’s body shape.