profile - دانشکده علوم
اعضای هیأت علمی دانشکده علوم
Soliman KHazaei
Associate Professor / Science / Statistics
Current courses
| Course Name | unit | term |
|---|---|---|
| probability theory advance | 4 | first semester Academic year 2026-2027 |
| matematical statistics I | 3 | first semester Academic year 2026-2027 |
| 2 | first semester Academic year 2026-2027 | |
| 3 | first semester Academic year 2026-2027 |
Master Theses
-
Smoothing spline density estimation from doubly truncated data
ABDULLAH ADNAN SAYAH 2026In many scientific fields, such as astronomy, survival analysis, and epidemiology, doubly truncated data are frequently encountered. In this type of data, the variable of interest is observable only if it falls between two random bounds (such as \\(U\\) and \\(V\\)). This sampling mechanism naturally introduces bias into the data, and consequently, conventional density estimators designed for complete data provide biased and inconsistent estimates of the true distribution.The present study aims to propose a nonparametric method for estimating the density function in the presence of doubly truncated data, based on smoothing splines. In this method, by employing the logistic transformation in the form of\\[ f(x)=\\frac{e^{\\eta(x)}}{\\int e^{\\eta(x)}\\,dx} \\]which automatically satisfies the intrinsic properties of a density function (non-negativity and integration to one), the problem is transformed into the minimization of a penalized likelihood function in a reproducing kernel Hilbert space (RKHS). This approach makes it possible to adjust for the bias induced by double truncation through the penalty term.The proposed method is validated through Monte Carlo simulations under various scenarios, and its performance is compared with that of the kernel density estimator (KDE). Furthermore, the practical effectiveness of the method is demonstrated through the analysis of two real-world datasets from the medical and industrial fields. The results indicate that the smoothing spline approach provides smoother, more accurate, and less biased estimates compared with the kernel-based method and can be employed as an efficient tool for analyzing incomplete data with a doubly truncated structure.
-
Semi-supervised Nonparametric Bayesian Clustering in the SHM structure.
Shahnaz Rahimi chegeni 2026 -
Forecasting time series with neural networks
Hadis Heidaryan 2024A time series is a set of data recorded over time. For example, we can refer to the time series of the price of a share in the stock market, the amount of rain in an area, etc. One of the most important goals of time series analysis is to predict its future values. Several statistical methods for predicting time series, such as the method of using time series analysis models of Autoregressive integrated moving average model and Seasonal autoregressive integrated moving average model, wavelet analysis methods have been in-troduced. Along with statistical methods, neural networks are also a powerful tool for predicting time series, due to the ability of neural networks to model relationships and complex patterns in data, predicting time series using it has attracted the attention of researchers in various fields and is a research topic. It has become popular. The use of convolutional neural networks to predict time series is known as an e?ective method for analyzing and predicting repetitive patterns in time data. These networks are designed to recognize di?erent patterns in temporal data and can make accurate predictions for future data values using these patterns. Long Short Term Memory (LSTM) Recurrent Neural Networks and Gate Recurrent Neural Networks (GRU) are two types of neural networks used for time series forecasting. LSTM and GRU networks are useful for time series forecasting due to their ability to retain memory over time. These networks, using a memory unit, keep the previous information and make the next prediction according to this information. In this thesis, time series forecasting with convolutional neural network and LSTM and GRU neural networks is investigated. The performance of these networks in prediction accuracy is compared. Also, their performance is compared with statistical methods such as SARIMA.Key ords. Forecasting time series, Neural networks, Recurrent neural networks, Long short-term memory, Gated recurrent unit, Convolutional neural networks.
-
Approximate Bayesian Computation via Classification
Fatemeh Moradi 2024Abstract In many challenges related to Bayesian inference, we face with some models that have certain complexities and it is necessary to calculate the likelihood function, which is difficult or impossible to calculate. This complexity makes it impossible to get the posterior distribution which is the basis of Bayesian inferences; so, as a solution, simulation methods can be used to estimate the model. One of the methods used in this field is the Approximate Bayesian Computation via >Keywords: ApproximateBayesianComputation, Kullback- Leibler (K-L) divergence, Bayesian inference,likelihood function, summary statistics,
-
Predicting the academic achievement of Razi University students using data mining techniques
Elnaz Kasani 2023يكي از عوامل مهم در بررسي آموزش، پيشبيني پيشرفت تحصيلي است و استفاده از فنون دادهكاوي يكي از راهكارهاي نوين پيشبيني پيشرفت تحصيلي است. در اين پاياننامه، فنون دادهكاوي در دو بخش روشهاي ساده شامل درخت تصميم، جنگل تصادفي، $K$-نزديكترين همسايه و بخش روشهاي پيچيدهتر شامل ماشين بردار پشتيبان و شبكه عصبي مورد مطالعه قرار گرفتهاند. همچنين دقت اين روشها بر روي مجموعه دادههاي مربوط به دانشجويان دانشگاه رازي از سال 1375 تا 1401 در مقطع كارداني و كارشناسي مورد بررسي و مقايسه قرار گرفته است. از روشهاي بررسي شده جنگل تصادفي بيشترين دقت پيشبيني را نتيجه داده است اما از لحاظ سرعت پاسخدهي هزينه محاسباتي بالايي دارد. روش $K$-نزديكترين همسايه از لحاظ دقت خيلي نزديك به روش جنگل تصادفي است با اين تفاوت كه زمان اندكي لازم است تا خروجيها حاصل شوند.
-
Approximating the Likelihood in Approximate Bayesian Computation
Mitra Havasi 2021 -
A comparison of binary classification methods for diagnosis of type of cancerous mass (malignant or benign) in breast cancer data
Mohsen Haghdost 2020reast cancer is one of the most common cancers in women today. Although men also get this cancer, the risk is more serious in women. Sometimes a misdiagnosis of cancer can lead to the death of a human being, and this should be considered a serious risk. Breast cancer tumors have two types, malignant and benign. Identifying the right type of these tumors will prevent unnecessary treatments and reduce mortality.The aim of this dissertation is to compare five methods of classification, naive Bayes, support vector machine, artificial neural network, logistic regression and random forest on breast cancer data to diagnose benign and malignant cancer tumors to determine the best method according to evaluation criteria. Choose binary, accuracy, precision, sensitivity, specificity, F1 score and Matthews correlation coefficient. The main criterion is to compare the accuracy of the model, then other criteria will be considered.
-
Estimation and Analysis of Urban Water Drinking Rate Function at Hamedan Water and Wastewater Company in 2019
Razieh Karami 2020 -
Diagonal quasi-newton methods
Foroozan Javaheri 2020Diagonal quasi-Newton method
-
Estimation approaches of Bayesian spectral density function
Hassan Naderi 2020Gaussian time-series models are often specified through their spectral density. Such models pose several computational challenges, in particular because of the non-sparse nature of the covariance matrix. We derive a fast approximation of the likelihood for such models. We use importance sampling to correct for the approximation error. We show that the variance of the importance sampling weights vanishes as the sample size goes to infinity. We show that the posterior is typically multi-modal, and derive a Sequential Monte Carlo sampler based on an annealing sequence in order to sample from the approximate posterior. Performance of the overall approach is evaluated on simulated and real datasets.
-
Simulation methods on the two parametres poisson dirichlet and the normalized inverse Gaussian processes
SEYEDEHSHIVA MOUSAVI 2020In this thesis, we develop simple, yet efficient, procedures for sampling approximations of the two-Parameter Poisson-Dirichlet Process and the normalized inverse- Gaussian process. We compare the efficiency of the new approximations to the corresponding stick-breaking approximations of the two-parameter Poisson-Dirichlet Process and the normalized inverse-Gaussian process, in which we demonstrate a substantial improvement.
-
Estimation of the survival function by using the copula for the inverse Rayleigh distribution.
LIQAA ALI ABBAS 2020Estimation of the survival function by using the copula for the inverse Rayleigh distribution.
-
MCMC Methods for Bayesian Mixtures of Copulas.
Kolsoom Hoseini deh abasani 2019Today, Copula’s use of the statistical functions which has increased dramatically. Although Copula functions have good advantages in statistical inferences, but when more than bivariate face, there are many computational problems. Therefore, using graphicmodels, wecananalysisthestructureofmulti-dimensionalCopula’swiththe dependenceofMarkovtreestructures. Butbecausethesizeofthevariablesincreases the structure of these graphical models are complex and time-consuming. Therefore, we can consider the conditions of models in a fully Bayesian framework contract. So that the tree and other tree-dependent parameters can be defined by the prior,and then get their posterior distributions. Because tree structures are related to each other variables, in this thesis using Markov Chain Monte Carlo simulation methods to compare the proposals of tree structures is investigated.
-
Applications of Nonparametric Bayesian Models to Problems in Natural Language Processing
Sanaz Samandari 2019در اين پايان نامه، كاربرد مدل هايبيز ناپارامتري در وظايف پردازش زبان طبيعي مورد مطالعه قرار داده شده اند. ابتدا روش هايبيز ناپارامتري براساس رايج ترين توزيع پيشين يعني فرايند ديريكله مورد مطالعهقرار گرفته اند. سپس نمايش هاي متفاوت از فرايند ديريكله مانند طرح كيسه پوليا،فرايند رستوران چيني و ساختار استيك بريكينگ معرفي شده اند. در ادامه به معرفي دو فرايند توليد شده توسط فرايندهاي ديريكلهيعني فرايندهايديريكله سلسله مراتبي و فرايندهاي پيتمن يور پرداخته شده است. در پايان 4 راه حلپيشنهادي بيز ناپارامتري در وظايف پردازش زبان طبيعي از جمله تقسيم بندي كلمه،استخراج عبارت و صف بندي، تجزيه مستقل از متن و مدلسازي زبان ارائه شده اند.
-
Estimation of survival function and the factors affecting patients with breast cancer in Iraq from 2014 to 2016
HASHEM MOHAMMED LATEF 2018برآورد تابع بقا و عوامل موثر بر بيماران مبتلا به سرطان پستان در عراق از سال 2014 تا 2016
-
Bayesian Nonparametric Density Function Estimation Under Length Bias
Saeid Sajedi 2017 -
The study on concepts of orthogonality in Hilbert c*-modules
2017In this thesis we consier tree concepts of orthogonlity in a Hilbert C?-module V over a C?-algebra A : the Birkhof-James orthogonality ?B , the strong Birkhof-ames orthogonlity ?SB , and the orthogonality with respect to the A-valued inner product on V . We characterize the classes of Hilbert C?-modules in which any two of them coincide .
-
Bayesian nonparametric regression with varying residual density
Azita Bahrami 2017 -
An application of cosine number transform for medical image encryption
Amin Salehi 2017امنيت يكي از اركان موجودات زنده و احساس امنيت يكي از اساسيترين نيازهاي نوع بشر است. امروزه با گستري وسايل ارتباطي و حجم اطلاعات مبادله شده در شبكههاي رايانهاي و همچنين توسعه و پيشرفتهاي صنعت مخابرات ند رسانه اي، مفهوم مخابرات تصويري متحول شده است. امنيت رسانه هاي ديجيتال يكي از مسائل مهم و مطرا جامعه رمزنگاري در دنياي امروز است. با توجه به كاربرد روزافزون رايانه و گستري زيرساخت هاي ارتباطي مثل شبكههاي سيار و اينترنت، حفظ محرمانگي و تاييد صحت تصاوير روز به روز اهميت بيشتري مييابد. با توجه به كاربرد روزافزون اينترنت و افزايش حجم اطلاعات مبادله شده، حفظ امنيت و تاييد صحت مخابره شده كه ميتواند كاربردهايي در امور تجاري، نظامي و حتي پزشكي داشته باشند نيز روز به روز اهميت بيشتري ميابد. در جهان ديجيتال امروزي امنيت تصاوير ديجيتال بيش از پيش اهميت پيدا كرده است. در سالهاي اخير سرعت زيادي در رشد انتقال تصاوير ديجيتال از طريق كامپيوتر بويژه اينترنت صورت گرفته است.به عنوان مثال ما در اين پاياننامه از يك روي رمزنگاري تصوير صحبت ميكنيم كه در امور پزشكي كه مرتبط با عكسبرداري از بيماران ميباشد و همچنين صحت و امنيت اطلاعات بيمار از اهميّت بالايي برخوردار است، استفاده ميشود. اين روي از رمزنگاري مبتني بر ميدان گالواست و ما آن را به طور كامل پيادهسازي كرده و علاوه بر بيان نقاط ضعف آن، راهي براي بهبود كارايي اين روي را بيان ميكنيم
-
A Predictive Study of Dirichlet Process Mixture Models for Curve Fitting
Sahar Shahbazi 2016 -
ازمون فرض بيز تجمعي در مدل رگرسيون دوجمله اي با توزيع هاي پيشين انتگرال
Liela Taimory yeganeh 2016 -
nonparametric bayesian inference by regression models in survival analysis
2015 -
naniparametric bayesian Inferece for mean Residual Life Function in Survival Analysis
SOMAYEH MORADI 2014

