Mohamad Saraee

Case-control study of stroke and the quality of hypertension control in north west England.

Abstract Objective: To examine the risk of stroke in relation to quality of hypertension control in routine general practice across an entire health district. Design: Population based matched case-control study. Setting: East Lancashire Health District with a participating population of 388 821 aged (80. Subjects: Cases were patients under 80 with their first stroke identified from a population based stroke register between 1 July 1994 and 30 June 1995. For each case two controls matched with the case for age and sex were selected from the same practice register. Hypertension was defined as systolic blood pressure !160 mm Hg or diastolic blood pressure !95 mm Hg, or both, on at least two occasions within any three month period or any history of treatment with antihypertensive drugs. Main outcome measures: Prevalence of hypertension and quality of control of hypertension (assessed by using the mean blood pressure recorded before stroke) and odds ratios of stroke (derived from conditional logistic regression). Results: Records of 267 cases and 534 controls were examined; 61% and 42% of these subjects respectively were hypertensive. Compared with non-hypertensive subjects hypertensive patients receiving treatment whose average pre-event systolic blood pressure was controlled to <140 mm Hg had an adjusted odds ratio for stroke of 1.3 (95% confidence interval 0.6 to 2.7). Those fairly well controlled (140-149 mm Hg), moderately controlled (150-159 mm Hg), or poorly controlled (!160 mm Hg) or untreated had progressively raised odds ratios of 1.6, 2.2, 3.2, and 3.5 respectively. Results for diastolic pressure were similar; both were independent of initial pressures before treatment. Around 21% of strokes were thus attributable to inadequate control with treatment, or 46 first events yearly per 100 000 population aged 40-79. Conclusions: Risk of stroke was clearly related to quality of control of blood pressure with treatment. In routine practice consistent control of blood pressure to below 150/90 mm Hg seems to be required for optimal stroke prevention. Key messages A case-control study based on the community stroke register and practice records showed a prevalence of hypertension of 61% for stroke patients and 42% in controls Quality of control of blood pressure was clearly related to the risk of stroke, independent of baseline blood pressure Detection and treatment rates of hypertension were high but control of blood pressure to below 150/90 mm Hg in treated hypertensive patients was only 33% in cases and 42% in controls When achieving optimal control of hypertension (to <150/90 mm Hg) in the most at risk and treatable age range (40-79 years) 86 hypertensive patients currently not well controlled need to be treated over five years to prevent one stroke

Care more about customers: Unsupervised domain-independent aspect detection for sentiment analysis of customer reviews

With the rapid growth of user-generated content on the internet, automatic sentiment analysis of online customer reviews has become a hot research topic recently, but due to variety and wide range of products and services being reviewed on the internet, the supervised and domain-specific models are often not practical. As the number of reviews expands, it is essential to develop an efficient sentiment analysis model that is capable of extracting product aspects and determining the sentiments for these aspects. In this paper, we propose a novel unsupervised and domain-independent model for detecting explicit and implicit aspects in reviews for sentiment analysis. In the model, first a generalized method is proposed to learn multi-word aspects and then a set of heuristic rules is employed to take into account the influence of an opinion word on detecting the aspect. Second a new metric based on mutual information and aspect frequency is proposed to score aspects with a new bootstrapping iterative algorithm. The presented bootstrapping algorithm works with an unsupervised seed set. Third, two pruning methods based on the relations between aspects in reviews are presented to remove incorrect aspects. Finally the model employs an approach which uses explicit aspects and opinion words to identify implicit aspects. Utilizing extracted polarity lexicon, the approach maps each opinion word in the lexicon to the set of pre-extracted explicit aspects with a co-occurrence metric. The proposed model was evaluated on a collection of English product review datasets. The model does not require any labeled training data and it can be easily applied to other languages or other domains such as movie reviews. Experimental results show considerable improvements of our model over conventional techniques including unsupervised and supervised approaches.

An Unsupervised Aspect Detection Model for Sentiment Analysis of Reviews

With the rapid growth of user-generated content on the internet, sentiment analysis of online reviews has become a hot research topic recently, but due to variety and wide range of products and services, the supervised and domain-specific models are often not practical. As the number of reviews expands, it is essential to develop an efficient sentiment analysis model that is capable of extracting product aspects and determining the sentiments for aspects. In this paper, we propose an unsupervised model for detecting aspects in reviews. In this model, first a generalized method is proposed to learn multi-word aspects. Second, a set of heuristic rules is employed to take into account the influence of an opinion word on detecting the aspect. Third a new metric based on mutual information and aspect frequency is proposed to score aspects with a new bootstrapping iterative algorithm. The presented bootstrapping algorithm works with an unsupervised seed set. Finally two pruning methods based on the relations between aspects in reviews are presented to remove incorrect aspects. The proposed model does not require labeled training data and can be applicable to other languages or domains. We demonstrate the effectiveness of our model on a collection of product reviews dataset, where it outperforms other techniques.

ADM-LDA: An aspect detection model based on topic modelling using the structure of review sentences

Probabilistic topic models are statistical methods whose aim is to discover the latent structure in a large collection of documents. The intuition behind topic models is that, by generating documents by latent topics, the word distribution for each topic can be modelled and the prior distribution over the topic learned. In this paper we propose to apply this concept by modelling the topics of sentences for the aspect detection problem in review documents in order to improve sentiment analysis systems. Aspect detection in sentiment analysis helps customers effectively navigate into detailed information about their features of interest. The proposed approach assumes that the aspects of words in a sentence form a Markov chain. The novelty of the model is the extraction of multiword aspects from text data while relaxing the bag-of-words assumption. Experimental results show that the model is indeed able to perform the task significantly better when compared with standard topic models.

Feature Selection Methods in Persian Sentiment Analysis

With the enormous growth of digital content in internet, various types of online reviews such as product and movie reviews present a wealth of subjective information that can be very helpful for potential users. Sentiment analysis aims to use automated tools to detect subjective information from reviews. Up to now as there are few researches conducted on feature selection in sentiment analysis, there are very rare works for Persian sentiment analysis. This paper considers the problem of sentiment classification using different feature selection methods for online customer reviews in Persian language. Three of the challenges of Persian text are using of a wide variety of declensional suffixes, different word spacing and many informal or colloquial words. In this paper we study these challenges by proposing a model for sentiment classification of Persian review documents. The proposed model is based on stemming and feature selection and is employed Naive Bayes algorithm for classification. We evaluate the performance of the model on a collection of cellphone reviews, where the results show the effectiveness of the proposed approaches.

A novel feature selection method for text classification using association rules and clustering

Readability and accuracy are two important features of any good classifier. For reasons such as acceptable accuracy, rapid training and high interpretability, associative classifiers have recently been used in many categorization tasks. Although features could be very useful in text classification, both training time and the number of produced rules will increase significantly owing to the high dimensionality of text documents. In this paper an association classification algorithm for text classification is proposed that includes a feature selection phase to select important features and a clustering phase based on class labels to tackle this shortcoming. The experimental results from applying the proposed algorithm in comparison with the results of selected well-known classification algorithms show that our approach outperforms others both in efficiency and in performance.

Time-sensitive influence maximization in social networks

One of the fundamental issues in social networks is the influence maximization problem, where the goal is to identify a small subset of individuals such that they can trigger the largest number of members in the network. In real-world social networks, the propagation of information from a node to another may incur a certain amount of time delay; moreover, the value of information may decrease over time. So not only the coverage size, but also the propagation speed matters. In this paper, we propose the Time-Sensitive Influence Maximization (TSIM) problem, which takes into account the time dependence of the information value. Considering the time delay aspect, we develop two diffusion models, namely the Delayed Independent Cascade model and the Delayed Linear Threshold model. We show that the TSIM problem is NP-hard under these models but the spread function is monotone and submodular. Thus, a greedy approximation algorithm can achieve a 1 − 1/e approximation ratio. Moreover, we propose two time-sensitive centrality measures and compare their performance with the greedy algorithm. We evaluate our methods on four real-world datasets. Experimental results show that the proposed algorithms outperform existing methods, which ignore the decay of information value over time.

Simulated annealing least squares twin support vector machine (SA-LSTSVM) for pattern classification

Least squares twin support vector machine (LSTSVM) is a relatively new version of support vector machine (SVM) based on non-parallel twin hyperplanes. Although, LSTSVM is an extremely efficient and fast algorithm for binary classification, its parameters depend on the nature of the problem. Problem dependent parameters make the process of tuning the algorithm with best values for parameters very difficult, which affects the accuracy of the algorithm. Simulated annealing (SA) is a random search technique proposed to find the global minimum of a cost function. It works by emulating the process where a metal slowly cooled so that its structure finally “freezes”. This freezing point happens at a minimum energy configuration. The goal of this paper is to improve the accuracy of the LSTSVM algorithm by hybridizing it with simulated annealing. Our research to date suggests that this improvement on the LSTSVM is made for the first time in this paper. Experimental results on several benchmark datasets demonstrate that the accuracy of the proposed algorithm is very promising when compared to other classification methods in the literature. In addition, computational time analysis of the algorithm showed the practicality of the proposed algorithm where the computational time of the algorithm falls between LSTSVM and SVM.

Effective pixel classification of Mars images based on ant colony optimization feature selection and extreme learning machine

one of the most important tasks of Mars rover, a robot which explores the Mars surface, is the process of automatic segmentation of images taken by front-line Panoramic Camera (Pancam). This procedure is highly significant since the transformation cost of images from Mars to earth is extremely high. Also, image analysis may help Mars rover for its navigation and localization. In this paper, a new feature vector including wavelet and color features for Mars images is proposed. Then, this feature vector is presented for extreme learning machine (ELM) classifier which leads to a high accuracy pixel classifier. It is shown that this system statistically outperforms support vector machine (SVM) and k-nearest neighbours (KNNs) classifiers with respect to both accuracy and run time. After that, dimension reduction in feature space is done by two proposed feature section algorithms based on ant colony optimization (ACO) to decrease the time complexity which is very important in Mars on-board applications. In the first proposed feature selection algorithm, the same feature subset is selected among the feature vector for all pixel classes, while in the second proposed algorithm, the most significant features are selected for each pixel class, separately. Proposed pixel classifier with complete feature set outperforms prior methods by 6.44% and 5.84% with respect to average Fmeasure and accuracy, respectively. Finally, proposed feature selection methods decrease the feature vector size up to 76% and achieves Fmeasure and accuracy of 91.72% and 91.05%, respectively, which outperforms prior methods with 87.22% and 86.64%.

A fuzzy method for discovering cost-effective actions from data

Data mining techniques are often confined to the delivery of frequent patterns and stop short of suggesting how to act on these patterns for business decision-making. They require human experts to post-process the discovered patterns manually. Therefore a significant need exists for techniques and tools with the ability to assist users in analyzing a large number of patterns to find usable knowledge. Action mining is one of these techniques which intelligently and automatically suggests some changes in the state of an object with the aim of gaining some profit in the corresponding domain. Up to now little research has been done in this field; in all cases continuous-valued data is handled by discretizing the associated attributes in advance or during the learning process. One inherent disadvantage in these methods is that using this sharp behavior can result in missing the optimal action. To overcome this problem this paper presents a method based on fuzzy set theory. In this paper, we concentrate on the fuzzy set based approach for the enhancement of Yangs method and present an algorithm that suggests actions which will decrease the degree to which a certain object belongs to an undesired status and increase the degree to which it belongs to a desired one. Our algorithm takes into account the fuzzy cost of actions, and further, it attempts to maximize the fuzzy net profit. The contribution of the work is in taking the output from fuzzy decision trees, and producing novel, actionable knowledge through automatic fuzzy post-processing. The performance of the proposed algorithm is compared with Yangs method using several real-life datasets taken from the UCI Machine Learning Repository. Experimental results show that the proposed algorithm outperforms Yangs method not only in finding more actions but also in finding actions with more fuzzy net profit.