با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد).
ردیف | عنوان | نوع |
---|---|---|
1 |
Analysis of factors that influence the performance of biometric systems based on EEG signals
تجزیه و تحلیل عوامل موثر بر عملکرد سیستم های بیومتریک بر اساس سیگنال های EEG-2021 Searching for new biometric traits is currently a necessity because traditional ones such as fingerprint, voice, or face are highly prone to forgery. For this reason, the study of bioelectric signals has the potential to develop new biometric systems. A motivation for using electroencephalogram signals is that they are unique to each person and are much more difficult to replicate than conventional biometrics. The objective of this study is to analyze the factors that influence the performance of a biometric system based on electroencephalogram signals. This work uses six different classifiers to compare several decomposition levels of the discrete wavelet transform as a preprocessing technique and also explores the importance of the recording time. These classifiers are Gaussian Naïve Bayes Classifier, K-Nearest Neighbors, Random Forest, AdaBoost, Support Vector Machine, and Multilayer Perceptron. This work proves that the decomposition level does not have a high impact on the overall result of the system. On the other hand, the recording time of electroencephalograms has a significant impact on the performance of the classifiers. It is worth mentioning that this study used two different datasets to validate the results. Finally, our experiments show that Support Vector Machine and AdaBoost are the bestclassifiers for this particular problem since they achieved a sensitivity, specificity, and accuracy of 85.94 ± 1.8, 99.55 ± 0.06, 99.12 ± 0.11 and 95.54 ± 0.53, 99.91 ± 0.01, and 99.83 ± 0.02 respectively. Keywords: Biometrics | Electroencephalogram | Discrete Wavelet Transform | Performance factors |
مقاله انگلیسی |
2 |
Process mining-based anomaly detection of additive manufacturing process activities using a game theory modeling approach
تشخیص ناهنجاری مبتنی بر استخراج فرآیند از فعالیت های فرآیند تولید مواد افزودنی با استفاده از رویکرد مدل سازی تئوری بازی-2020 As a new production procedure Additive Manufacturing will present a time-effective production system when adopted in distributed 3D printing mode. In this case, the distributed manufacturing leads to different challenges such as control between production sites. Based on the cloud infrastructure usage for distributed production systems, the product reliability handling is vital. Moreover, AM is used to produce safety–critical systems components and this product type defines AM as an interesting attack target. This study presents a new extension of uncertain Business Process Management System (uncertain BPMS) architecture for detecting anomaly using this extension capability. This extension has a new component as event-based anomaly detector, where intrusion detection can take place through an integration of process mining and game theory techniques. The proposed component could operate based on pre-processor, conformance checker, and anomaly detection optimizer modules. These modules can intelligently control the AM process activities between expected behavior and actual behavior using distributed event logs, a hybrid of highly accurate algorithms such as Improved Particle Swarm Optimization (IPSO), firefly, and AdaBoost algorithms inside the game theory modeling approach. In this case, the game theory technique as an optimizer provides optimal selection strategies for the proposed component to detect untrusted behaviors. The results of the new extension execution on a case study and its evaluation using Nash Equilibrium (NE) solution indicate that the proposed anomaly detector component is highly accurate in anomaly detection for AM process activities and can detect more attacks successfully through guidance of the game theory framework in the system. Keywords: Event-based anomaly detection | Additive manufacturing | Business process management system | Process mining technique | Game theory modeling | Distributed production system |
مقاله انگلیسی |
3 |
An ensemble method for inverse reinforcement learning
یک روش گروهی برای یادگیری تقویتی معکوس-2020 In inverse reinforcement learning (IRL), a reward function is learnt to generalize experts’
behavior. This paper proposes a model-free IRL algorithm based on an ensemble method,
where the reward function is regarded as a parametric function of expected features. In
other words, the parameters are updated based on a weak classification method. The IRL
is formulated as a problem of a boosting classifier, akin to the renowned Adaboost algorithm
for classification, feature expectations from experts’ demonstration, and the trajectory
induced by an agent’s current policy. The proposed approach takes individual feature
expectation as attractor or expeller, depending on the sign of the residuals of the state
trajectories between expert’s demonstration and the one induced by RL with the currently
approximated reward function, so as to tackle its central challenges of accurate inference,
generalizability, and correctness of prior knowledge. Then, the proposed method is applied
further to approximate an abstract reward function from observations of more complex behavior
composed of several basic actions. The results of the simulations in a labyrinth are
shown to validate the proposed algorithm. Furthermore, behaviors composed of a set of
primitive actions on a soccer robot field are examined for the applicability of the proposed
method. Keywords: Apprentice learning | Inverse reinforcement learning | Q-learning | Boosting classifier |
مقاله انگلیسی |
4 |
An end-to-end inverse reinforcement learning by a boosting approach with relative entropy
یک یادگیری تقویت معکوس پایان به پایان با یک رویکرد تقویتی با آنتروپی نسبی-2020 Inverse reinforcement learning (IRL) involves imitating expert behaviors by recovering re- ward functions from demonstrations. This study proposes a model-free IRL algorithm to solve the dilemma of predicting the unknown reward function. The proposed end-to-end model comprises a dual structure of autoencoders in parallel. The model uses a state encoding method to reduce the computational complexity for high-dimensional environ- ments and utilizes an Adaboost classifier to determine the difference between the pre- dicted and demonstrated reward functions. Relative entropy is used as a metric to measure the difference between the demonstrated and the imitated behavior. The simulation exper- iments demonstrate the effectiveness of the proposed method in terms of the number of iterations that are required for the estimation. Keywords: Inverse reinforcement learning | Imitation learning | State encoding | Adaboost | Relative entropy |
مقاله انگلیسی |
5 |
Detection of power grid disturbances and cyber-attacks based on machine learning
تشخیص اختلالات شبکه برق و حملات سایبری بر اساس یادگیری ماشین-2019 Modern intelligent power grid provides an efficient way of managing energy supply and consumption while facing numerous security threats at the same time. Both natural and man-made events can cause power system disturbance. Therefore, it is important for operators to identify the specific causes and types of disturbance in the power system to make decisions and respond appropriately. In order to address this problem, this paper proposes an attack detection model for power system based on ma- chine learning that can be trained by using information and logs collected by phasor measurement units (PMUs). We carry out feature construction engineering, and then send the data to different machine learning models, in which random forest is chosen as the basic classifier of AdaBoost. The model is evalu- ated using open-source simulated power system data, which consists of 37 power system event scenarios. Finally, we compare the proposed model with other models by using different evaluation metrics. As the experimental results demonstrate that this model can achieve accuracy rate of 93.91% and detection rate of 93.6%, higher than eight recently developed techniques. Keywords: Machine learning algorithm | Network attack | Feature construction engineering | Data processing |
مقاله انگلیسی |
6 |
Application of adaptive boosting (AdaBoost) in demand-driven acquisition (DDA) prediction: A machine-learning approach
کاربرد تقویت سازگاری (AdaBoost) در پیش بینی تمایل محور (DDA): یک رویکرد یادگیری ماشین-2019 Demand-driven acquisition (DDA) programs are playing an increasingly important role in academic libraries.
However, the literature surrounding this topic illustrates the wide-ranging, and frequently unpredictable, results
of DDA implementation. As uncertainty abounds, librarians continue to seek out deeper understandings of those
processes driving the use and purchase of DDA materials. Implicit in this search is a desire to understand how
local environmental factors and user preferences dictate broader collection use and purchasing patterns. A small
number of these studies have sought deeper insights through predictive modeling, though success has been
limited. Following this line of inquiry, this study explores how machine learning might enable more effective
collection development and management strategies through the predictive modeling of complex collection use
and purchasing patterns. This research describes a replicable implementation of an adaptive boosting (AdaBoost)
model that predicts the likelihood of DDA titles being triggered for purchase. The predictive capacity of this
model is compared against a more traditional logistic regression model. This studys results show that the
AdaBoost model possesses much higher predictive capacity than a regression-based model informed by the same
set of predictors. The AdaBoost algorithm, once trained with local DDA data, provides accurate predictions in
82% of cases. Keywords: Acquisitions | Assessment | DDA | Machine learning | Boosting |
مقاله انگلیسی |
7 |
An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction
یک مدل ماشین پیشرفته افراطی برای پیش بینی جریان رودخانه: پیشرفته ترین برنامه ها ، کاربردهای عملی در منطقه مهندسی منابع آب و جهت گیری تحقیقات آینده-2019 Despite the massive diversity in the modeling requirements for practical hydrological applications, there remains
a need to develop more reliable and intelligent expert systems used for real-time prediction purposes. The
challenge in meeting the standards of an expert system is primarily due to the influence and behavior of hydrological
processes that is driven by natural fluctuations over the physical scale, and the resulting variance in
the underlying model input datasets. River flow forecasting is an imperative task for water resources operation
and management, water demand assessments, irrigation and agriculture, early flood warning and hydropower
generations. This paper aims to investigate the viability of the enhanced version of extreme learning machine
(EELM) model in river flow forecasting applied in a tropical environment. Herein, we apply the complete orthogonal
decomposition (COD) learning tool to tune the output-hidden layer of the ELM model’s internal neuronal
system, instead of the conventional multi-resolution tool (e.g., singular value decomposition). ToA-ELM, AdaBoost.RT-extreme learning machine; AI, artificial intelligence; ANFIS, adaptive neuro-fuzzy inference system; ANN, artificial neural
network; ARIMA, autoregressive integrated moving average; AtmP, atmospheric pressure; B-ANN, bootstrap-artificial neural network; BCSO, binary-coded swarm
optimization; B-ELM, bootstrap-extreme learning machine; C-ELM, complex-extreme learning machine; Cl−1, chloride; COD, complete orthogonal decomposition
(COD); CRO-ELM, coral reefs optimization-extreme learning machine; DE-ELM, deferential evolution-extreme learning machine; DID, department of Irrigation and
Drainage; DO, dissolved oxygen concentration; EC-SVR, evolutionary computation-based support vector machine; EDI, effective drought index; ELM, extreme
learning machine; EELM, enhanced extreme learning machine; EEMD, ensemble empirical mode decomposition; EL-ANFIS, extreme learning adaptive neuro-fuzzy
inference system; EMD, empirical mode decomposition; Ens, Nash-Sutcliffe coefficient; Ensemble-ELM, ensemble-extreme learning machine; EPR, evolutionary
polynomial regression; ESNs, echo state networks; ETo, evapotranspiration; Fe, iron; Fr, Froude number; FS, factor of safety; GA-ELM, genetic algorithm-extreme
learning machine; GCM, general circulation model; G-ELM, geomorphology extreme learning machine; GP, genetic programming; GRNN, generalized regression
neural network; HCO3
-1, bicarbonate; HDSR, diffuse solar radiation; HRT, hydraulic retention time; I-ELM, integrated extreme learning machine; KELM, Kernelextreme
learning machine; LST, land surface temperature; LASSO, least absolute shrinkage and selection operator; LSTM, long short-term memory network; LSSVM,
least square support vector machine; MAE, mean absolute error; MARS, multivariate adaptive regression spline; MBFIPS, Multi-objective binary-coded fully informed
particle swarm optimization; MC-OS-ELM, meta cognitive-online sequential-extreme learning machine; MLPNN, multi-linear perceptron neural network; MLR,
multiple linear regression; MME, multi-model ensemble; NEMR, northeast monsoon rainfall; NO2
-1, nitrite; NO3
-1, nitrate; NO2, nitrogen dioxide; NT, total nitrogen;
O3, ozone; OP-ELM, optimally pruned-extreme learning machine; OSELM, online sequential extreme learning machine; PCA, principal component analysis; pH,
power of hydrogen; PM10, air pollution “suspended particulate matters”; PO4
-3, phosphorus; R-ELM, radial basis-extreme learning machine; r, determination coefficient;
RE, relative error; RF, rainfall; RH, relative humidity; RHmax, maximum relative humidity; RHmean, mean relative humidity; RHmin, minimum relative
humidity; RMSE, root mean square error; RVM, relevance vector machine; SaE-ELM, self-adaptive evolutionary-extreme learning machine; SC, specific conductance;
S-ELM, sigmoid-extreme learning machine; SHr, sunshine hour; SR, solar radiation; SO4
-2, sulfate; SiO2, Silicon; SO2, |
مقاله انگلیسی |
8 |
Evaluating multi-label classifiers and recommender systems in the financial service sector
ارزیابی طبقه بندی کننده های چند برچسبی و سیستم های توصیه گر در بخش خدمات مالی-2019 The objective of this paper is to evaluate multi-label classification techniques and recommender systems for cross-sell purposes in the financial services sector. We carried out three analyses using data obtained from an international financial services provider. First, we tested four multi-label classification techniques, of which the two problem transformation methods were combined with several base classifiers. Second, we benchmarked the performance of five state-of-the-art recommender approaches. Third, we compared the best performing multi-label classification and recommender approaches with each other. The re- sults identify user-based collaborative filtering as the top performing recommender system, with a cross- validated F 1 measure of 42.20% and G -mean of 42.64%. Classifier chains binary relevance with adaboost and binary relevance with random forest are the top performing multi-label classification algorithms for respectively F 1 measure and G -mean, yielding a cross-validated F 1 measure of 53.33% and G -mean of 54.37%. The statistical comparison between the best performing approaches confirms the superiority of multi-label classification techniques. Our study provides important recommendations for financial ser- vices providers, who are interested in the most effective methods to determine cross-sell opportunities. In previous studies, multi-label classification techniques and recommender systems were always inves- tigated independently of each other. To the best of our knowledge, our study is therefore the first to compare both techniques in the financial services sector. Keywords: OR in marketing | CRM | Predictive modeling | Multi-label classifiers | Recommender systems |
مقاله انگلیسی |
9 |
Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms
خصوصیات آماری و طبقه بندی داده های بیان ژن ریزآرایه روده بزرگ با استفاده از چند پارادایم یادگیری ماشین-2019 Objective: A colon microarray data is a repository of thousands of gene expressions with different strengths for each cancer cell. It is necessary to detect which genes are responsible for cancer growth. This study presents an exhaustive comparative study of different machine learning (ML) systems which serves two major purposes: (a) identification of high risk differential genes using statistical tests and (b) development of a ML strategy for predicting cancer genes. Methods: Four statistical tests namely: Wilcoxon sign rank sum (WCSRS), t test, Kruskal–Wallis (KW), and F-test were adapted for cancerous gene identification using their p-values. The extracted gene set was used to classify cancer patients using ten classifiers namely: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), naïve Bayes (NB), Gaussian process classification (GPC), support vector ma- chine (SVM), artificial neural network (ANN), logistic regression (LR), decision tree (DT), Adaboost (AB), and random forest (RF). Performance was then evaluated using cross-validation protocols and standard- ized metrics viz. accuracy (ACC) and area under the curve (AUC). Results: The colon cancer dataset consists of 20 0 0 genes from 62 patients (40 cancer vs. 22 control). The overall mean ACC of our ML system using all four statistical tests and all ten classifiers was 90.50 %. The ML system showed an ACC of 99.81% using a combination WCSRS test and RF-based classifier. This is an improvement of 8% over previously published values in literature. Conclusions: RF-based model with statistical tests for detection of high risk genes showed the best per- formance for accurate cancer classification in multi-center clinical trials. Keywords: Colon cancer | Gene expression data | Prediction | Statistical test | Machine learning | Performance |
مقاله انگلیسی |
10 |
Comparison of skin disease prediction by feature selection using ensemble data mining techniques
مقایسه پیش بینی بیماری پوستی با انتخاب ویژگی ها با استفاده از تکنیک های داده کاوی گروه-2019 Background: Skin disease is a major problem among people worldwide. Different machine learning techniques
can be applied to identify classes of skin disease. Herein, we have applied machine learning algorithms to
categorize classes of skin disease using ensemble techniques, and then a feature selection method is utilized to
compare the results obtained.
Method: In the proposed study, we present a new method which applies six different data mining classification
techniques, and then develop an ensemble approach using Bagging, AdaBoost and Gradient Boosting classifier
techniques to predict classes of skin disease. Furthermore, a feature importance method is utilized to select the
most salient 15 features which will play a major role in prediction. A subset of the original dataset is obtained
after selecting the 15 features, to compare the results of six machine learning techniques, and an ensemble
approach is applied to the entire dataset.
Results: The ensemble method is compared with the subset obtained from the feature selection method. The
outcome shows that the dermatological prediction accuracy of the test dataset is increased as compared to the
use of an individual classifier, and improved accuracy is obtained as compared with the feature selection subset
method.
Conclusion: The ensemble method and feature selection applied to dermatology datasets yields a better performance
as compared to individual classifier algorithms. The ensemble method provides a more accurate and
effective skin disease prediction. Keywords: Skin disease | Dermatology | Extra tree classifier | Radius neighbors classifier | Passive aggressive classifier |
مقاله انگلیسی |