The most significant practical challenge for face recognition is perhaps variability in lighting intensity. In this paper, we developed a face recognition which is insensitive to large variation in illumination. Norma...The most significant practical challenge for face recognition is perhaps variability in lighting intensity. In this paper, we developed a face recognition which is insensitive to large variation in illumination. Normalization step including two steps, first we used Histogram truncation as a pre-processing step and then we implemented Homomorphic filter. The main idea is that, achieving illumination invariance causes to simplify feature extraction module and increases recognition rate. Then we utilized Fuzzy Linear Discriminant Analysis (FLDA) in feature extraction stage which showed a good discriminating ability compared to other methods while classification is performed using Feedforward Neural Network (FFNN). The experiments were performed on the ORL (Olivetti Research Laboratory) face image database and the results show the present method outweighs other techniques applied on the same database and reported in literature.展开更多
Mohan et al.developed a feed-forward neural network(FFNN)model to predict Kamlet-Taft parameters using quantum chemically derived features,achieving notable predictive accuracy.However,this study raises concerns about...Mohan et al.developed a feed-forward neural network(FFNN)model to predict Kamlet-Taft parameters using quantum chemically derived features,achieving notable predictive accuracy.However,this study raises concerns about conflating prediction accuracy with feature importance accuracy,as high R^(2)and low root mean square error(RMSE)do not guarantee valid feature importance assessments.The reliance on SHapley Additive exPlanations(SHAP)for feature evaluation is problematic due to model-specific biases that could misrepresent true associations.A broader understanding of data distribution,statistical relationships,and significance testing through pvalues is essential to rectify this.This paper advocates for employing robust statistical methods,like Spearman's correlation,to effectively assess genuine associations and mitigate biases in feature importance analysis.展开更多
The problem of effluent total nitrogen(TN)at most of the wastewater treatment plants(WWTPs)in China is important for meeting the related water quality standards,even under the condition of high energy consumption.To a...The problem of effluent total nitrogen(TN)at most of the wastewater treatment plants(WWTPs)in China is important for meeting the related water quality standards,even under the condition of high energy consumption.To achieve better prediction and control of effluent TN concentration,an efficient prediction model,based on controllable operation parameters,was constructed in a sequencing batch reactor process.Compared with previous models,this model has two main characteristics:①Superficial gas velocity and anoxic time are controllable operation parameters and are selected as the main input parameters instead of dissolved oxygen to improve the model controllability,and②the model prediction accuracy is improved on the basis of a feedforward neural network(FFNN)with algorithm optimization.The results demonstrated that the FFNN model was efficiently optimized by scaled conjugate gradient,and the performance was excellent compared with other models in terms of the correlation coefficient(R).The optimized FFNN model could provide an accurate prediction of effluent TN based on influent water parameters and key control parameters.This study revealed the possible application of the optimized FFNN model for the efficient removal of pollutants and lower energy consumption at most of the WWTPs.展开更多
The rapid advancement of wireless communication is forming a hyper-connected 5G network in which billions of linked devices generate massive amounts of data.The traffic control and data forwarding functions are decoup...The rapid advancement of wireless communication is forming a hyper-connected 5G network in which billions of linked devices generate massive amounts of data.The traffic control and data forwarding functions are decoupled in software-defined networking(SDN)and allow the network to be programmable.Each switch in SDN keeps track of forwarding information in a flow table.The SDN switches must search the flow table for the flow rules that match the packets to handle the incoming packets.Due to the obvious vast quantity of data in data centres,the capacity of the flow table restricts the data plane’s forwarding capabilities.So,the SDN must handle traffic from across the whole network.The flow table depends on Ternary Content Addressable Memorable Memory(TCAM)for storing and a quick search of regulations;it is restricted in capacity owing to its elevated cost and energy consumption.Whenever the flow table is abused and overflowing,the usual regulations cannot be executed quickly.In this case,we consider lowrate flow table overflowing that causes collision flow rules to be installed and consumes excessive existing flow table capacity by delivering packets that don’t fit the flow table at a low rate.This study introduces machine learning techniques for detecting and categorizing low-rate collision flows table in SDN,using Feed ForwardNeuralNetwork(FFNN),K-Means,and Decision Tree(DT).We generate two network topologies,Fat Tree and Simple Tree Topologies,with the Mininet simulator and coupled to the OpenDayLight(ODL)controller.The efficiency and efficacy of the suggested algorithms are assessed using several assessment indicators such as success rate query,propagation delay,overall dropped packets,energy consumption,bandwidth usage,latency rate,and throughput.The findings showed that the suggested technique to tackle the flow table congestion problem minimizes the number of flows while retaining the statistical consistency of the 5G network.By putting the proposed flow method and checking whether a packet may move from point A to point B without breaking certain regulations,the evaluation tool examines every flow against a set of criteria.The FFNN with DT and K-means algorithms obtain accuracies of 96.29%and 97.51%,respectively,in the identification of collision flows,according to the experimental outcome when associated with existing methods from the literature.展开更多
Deep learning(DL)is a subdivision of machine learning(ML)that employs numerous algorithms,each of which provides various explanations of the data it consumes;mobile ad-hoc networks(MANET)are growing in promi-nence.For...Deep learning(DL)is a subdivision of machine learning(ML)that employs numerous algorithms,each of which provides various explanations of the data it consumes;mobile ad-hoc networks(MANET)are growing in promi-nence.For reasons including node mobility,due to MANET’s potential to provide small-cost solutions for real-world contact challenges,decentralized management,and restricted bandwidth,MANETs are more vulnerable to security threats.When protecting MANETs from attack,encryption and authentication schemes have their limits.However,deep learning(DL)approaches in intrusion detection sys-tems(IDS)can adapt to the changing environment of MANETs and allow a sys-tem to make intrusion decisions while learning about its mobility in the environment.IDSs are a secondary defiance system for mobile ad-hoc networks vs.attacks since they monitor network traffic and report anything unusual.Recently,many scientists have employed deep neural networks(DNNs)to address intrusion detection concerns.This paper used MANET to recognize com-plex patterns by focusing on security standards through efficiency determination and identifying malicious nodes,and mitigating network attacks using the three algorithms presented Cascading Back Propagation Neural Network(CBPNN),Feedforward-Neural-Network(FNN),and Cascading-Back-Propagation-Neural-Network(CBPNN)(FFNN).In addition to Convolutional-Neural-Network(CNN),these primary forms of deep neural network(DNN)building designs are widely used to improve the performance of intrusion detection systems(IDS)and the use of IDS in conjunction with machine learning(ML).Further-more,machine learning(ML)techniques than their statistical and logical methods provide MANET network learning capabilities and encourage adaptation to differ-ent environments.Compared with another current model,The proposed model has better average receiving packet(ARP)and end-to-end(E2E)performance.The results have been obtained from CBP,FFNN and CNN 74%,82%and 85%,respectively,by the time(27,18,and 17 s).展开更多
In the oil industry, the productivity of oil wells depends on the performance of the sub-surface equipment system. These systems often have problems stemming from sand, corrosion, internal pressure variation, or other...In the oil industry, the productivity of oil wells depends on the performance of the sub-surface equipment system. These systems often have problems stemming from sand, corrosion, internal pressure variation, or other factors. In order to ensure high equipment performance and avoid high-cost losses, it is essential to identify the source of possible failures in the early stage. However, this requires additional maintenance fees and human power. Moreover, the losses caused by these problems may lead to interruptions in the whole production process. In order to minimize maintenance costs, in this paper, we introduce a model for predicting equipment failure based on processing the historical data collected from multiple sensors. The state of the system is predicted by a Feed-Forward Neural Network (FFNN) with an SGD and Backpropagation algorithm is applied in the training process. Our model’s primary goal is to identify potential malfunctions at an early stage to ensure the production process’ continued high performance. We also evaluated the effectiveness of our model against other solutions currently available in the industry. The results of our study show that the FFNN can attain an accuracy score of 97% on the given dataset, which exceeds the performance of the models provided.展开更多
COVID-19 has created a pandemic situation in the whole world.Controlling of COVID-19 spreading rate in the social environment is a challenge for all individuals.In the present study,simulation of the lockdown effect o...COVID-19 has created a pandemic situation in the whole world.Controlling of COVID-19 spreading rate in the social environment is a challenge for all individuals.In the present study,simulation of the lockdown effect on the COVID-19 spreading rate in India and mapping of its recovery percentage(until May 2020)were investigated.Investigation of the lockdown impact dependent on first order reaction kinetics demonstrated higher effect of lockdown 1 on controlling the COVID-19 spreading rate when contrasted with lockdown 2 and 3.Although decreasing trend was followed for the reaction rate constant of different lockdown stages,the distinction between the lockdown 2 and 3 was minimal.Mathematical and feed forward neural network(FFNN)approaches were applied for the simulation of COVID-19 spreading rate.In case of mathematical approach,exponential model indicated adequate performance for the prediction of the spreading rate behavior.For the FFNN based modeling,1-5-1 was selected as the best architecture so as to predict adequate spreading rate for all the cases.The architecture also showed effective performance in order to forecast number of cases for next 14 days.The recovery percentage was modeled as a function of number of days with the assistance of polynomial fitting.Therefore,the investigation recommends proper social distancing and efficient management of corona virus in order to achieve higher decreasing trend of reaction rate constant and required recovery percentage for the stabilization of India.展开更多
文摘The most significant practical challenge for face recognition is perhaps variability in lighting intensity. In this paper, we developed a face recognition which is insensitive to large variation in illumination. Normalization step including two steps, first we used Histogram truncation as a pre-processing step and then we implemented Homomorphic filter. The main idea is that, achieving illumination invariance causes to simplify feature extraction module and increases recognition rate. Then we utilized Fuzzy Linear Discriminant Analysis (FLDA) in feature extraction stage which showed a good discriminating ability compared to other methods while classification is performed using Feedforward Neural Network (FFNN). The experiments were performed on the ORL (Olivetti Research Laboratory) face image database and the results show the present method outweighs other techniques applied on the same database and reported in literature.
文摘Mohan et al.developed a feed-forward neural network(FFNN)model to predict Kamlet-Taft parameters using quantum chemically derived features,achieving notable predictive accuracy.However,this study raises concerns about conflating prediction accuracy with feature importance accuracy,as high R^(2)and low root mean square error(RMSE)do not guarantee valid feature importance assessments.The reliance on SHapley Additive exPlanations(SHAP)for feature evaluation is problematic due to model-specific biases that could misrepresent true associations.A broader understanding of data distribution,statistical relationships,and significance testing through pvalues is essential to rectify this.This paper advocates for employing robust statistical methods,like Spearman's correlation,to effectively assess genuine associations and mitigate biases in feature importance analysis.
基金This work was funded by the Major Science and Technology Program for Water Pollution Control and Treatment(2017ZX07201003)the National Natural Science Foundation of China(51961125101)the Science and Technology Project of Zhejiang Province(2018C03003).
文摘The problem of effluent total nitrogen(TN)at most of the wastewater treatment plants(WWTPs)in China is important for meeting the related water quality standards,even under the condition of high energy consumption.To achieve better prediction and control of effluent TN concentration,an efficient prediction model,based on controllable operation parameters,was constructed in a sequencing batch reactor process.Compared with previous models,this model has two main characteristics:①Superficial gas velocity and anoxic time are controllable operation parameters and are selected as the main input parameters instead of dissolved oxygen to improve the model controllability,and②the model prediction accuracy is improved on the basis of a feedforward neural network(FFNN)with algorithm optimization.The results demonstrated that the FFNN model was efficiently optimized by scaled conjugate gradient,and the performance was excellent compared with other models in terms of the correlation coefficient(R).The optimized FFNN model could provide an accurate prediction of effluent TN based on influent water parameters and key control parameters.This study revealed the possible application of the optimized FFNN model for the efficient removal of pollutants and lower energy consumption at most of the WWTPs.
基金Taif University Researchers supporting Project number(TURSP-2020/215),Taif University,Taif,Saudi Arabia.
文摘The rapid advancement of wireless communication is forming a hyper-connected 5G network in which billions of linked devices generate massive amounts of data.The traffic control and data forwarding functions are decoupled in software-defined networking(SDN)and allow the network to be programmable.Each switch in SDN keeps track of forwarding information in a flow table.The SDN switches must search the flow table for the flow rules that match the packets to handle the incoming packets.Due to the obvious vast quantity of data in data centres,the capacity of the flow table restricts the data plane’s forwarding capabilities.So,the SDN must handle traffic from across the whole network.The flow table depends on Ternary Content Addressable Memorable Memory(TCAM)for storing and a quick search of regulations;it is restricted in capacity owing to its elevated cost and energy consumption.Whenever the flow table is abused and overflowing,the usual regulations cannot be executed quickly.In this case,we consider lowrate flow table overflowing that causes collision flow rules to be installed and consumes excessive existing flow table capacity by delivering packets that don’t fit the flow table at a low rate.This study introduces machine learning techniques for detecting and categorizing low-rate collision flows table in SDN,using Feed ForwardNeuralNetwork(FFNN),K-Means,and Decision Tree(DT).We generate two network topologies,Fat Tree and Simple Tree Topologies,with the Mininet simulator and coupled to the OpenDayLight(ODL)controller.The efficiency and efficacy of the suggested algorithms are assessed using several assessment indicators such as success rate query,propagation delay,overall dropped packets,energy consumption,bandwidth usage,latency rate,and throughput.The findings showed that the suggested technique to tackle the flow table congestion problem minimizes the number of flows while retaining the statistical consistency of the 5G network.By putting the proposed flow method and checking whether a packet may move from point A to point B without breaking certain regulations,the evaluation tool examines every flow against a set of criteria.The FFNN with DT and K-means algorithms obtain accuracies of 96.29%and 97.51%,respectively,in the identification of collision flows,according to the experimental outcome when associated with existing methods from the literature.
文摘Deep learning(DL)is a subdivision of machine learning(ML)that employs numerous algorithms,each of which provides various explanations of the data it consumes;mobile ad-hoc networks(MANET)are growing in promi-nence.For reasons including node mobility,due to MANET’s potential to provide small-cost solutions for real-world contact challenges,decentralized management,and restricted bandwidth,MANETs are more vulnerable to security threats.When protecting MANETs from attack,encryption and authentication schemes have their limits.However,deep learning(DL)approaches in intrusion detection sys-tems(IDS)can adapt to the changing environment of MANETs and allow a sys-tem to make intrusion decisions while learning about its mobility in the environment.IDSs are a secondary defiance system for mobile ad-hoc networks vs.attacks since they monitor network traffic and report anything unusual.Recently,many scientists have employed deep neural networks(DNNs)to address intrusion detection concerns.This paper used MANET to recognize com-plex patterns by focusing on security standards through efficiency determination and identifying malicious nodes,and mitigating network attacks using the three algorithms presented Cascading Back Propagation Neural Network(CBPNN),Feedforward-Neural-Network(FNN),and Cascading-Back-Propagation-Neural-Network(CBPNN)(FFNN).In addition to Convolutional-Neural-Network(CNN),these primary forms of deep neural network(DNN)building designs are widely used to improve the performance of intrusion detection systems(IDS)and the use of IDS in conjunction with machine learning(ML).Further-more,machine learning(ML)techniques than their statistical and logical methods provide MANET network learning capabilities and encourage adaptation to differ-ent environments.Compared with another current model,The proposed model has better average receiving packet(ARP)and end-to-end(E2E)performance.The results have been obtained from CBP,FFNN and CNN 74%,82%and 85%,respectively,by the time(27,18,and 17 s).
文摘In the oil industry, the productivity of oil wells depends on the performance of the sub-surface equipment system. These systems often have problems stemming from sand, corrosion, internal pressure variation, or other factors. In order to ensure high equipment performance and avoid high-cost losses, it is essential to identify the source of possible failures in the early stage. However, this requires additional maintenance fees and human power. Moreover, the losses caused by these problems may lead to interruptions in the whole production process. In order to minimize maintenance costs, in this paper, we introduce a model for predicting equipment failure based on processing the historical data collected from multiple sensors. The state of the system is predicted by a Feed-Forward Neural Network (FFNN) with an SGD and Backpropagation algorithm is applied in the training process. Our model’s primary goal is to identify potential malfunctions at an early stage to ensure the production process’ continued high performance. We also evaluated the effectiveness of our model against other solutions currently available in the industry. The results of our study show that the FFNN can attain an accuracy score of 97% on the given dataset, which exceeds the performance of the models provided.
文摘COVID-19 has created a pandemic situation in the whole world.Controlling of COVID-19 spreading rate in the social environment is a challenge for all individuals.In the present study,simulation of the lockdown effect on the COVID-19 spreading rate in India and mapping of its recovery percentage(until May 2020)were investigated.Investigation of the lockdown impact dependent on first order reaction kinetics demonstrated higher effect of lockdown 1 on controlling the COVID-19 spreading rate when contrasted with lockdown 2 and 3.Although decreasing trend was followed for the reaction rate constant of different lockdown stages,the distinction between the lockdown 2 and 3 was minimal.Mathematical and feed forward neural network(FFNN)approaches were applied for the simulation of COVID-19 spreading rate.In case of mathematical approach,exponential model indicated adequate performance for the prediction of the spreading rate behavior.For the FFNN based modeling,1-5-1 was selected as the best architecture so as to predict adequate spreading rate for all the cases.The architecture also showed effective performance in order to forecast number of cases for next 14 days.The recovery percentage was modeled as a function of number of days with the assistance of polynomial fitting.Therefore,the investigation recommends proper social distancing and efficient management of corona virus in order to achieve higher decreasing trend of reaction rate constant and required recovery percentage for the stabilization of India.
