Muhammad Nazir

Gender classification using image processing techniques: A survey

Classification has emerged as a leading technique for problem solution and optimization. Classification has been used extensively in several problems domains. Automated gender classification is an area of great significance and has great potential for future research. It offers several industrial applications in near future such as monitoring, surveillance, commercial profiling and human computer interaction. Different methods have been proposed for gender classification like gait, iris and hand shape. However, majority of techniques for gender classification are based on facial information. In this paper, a comparative study of gender classification using different techniques is presented. The major emphasis of this work is on the critical evaluation of different techniques used for gender classification. The comparative evaluation has highlighted major strengths and limitations of existing gender classification techniques. Taking an overview of these major problems, our research is focused on summarizing the literature by highlighting its strengths and limitations. This study also presents several areas of future research in the domain of gender classification.

Heart disease classification ensemble optimization using Genetic algorithm

Heart disease diagnosis is considered as one of the complicated tasks in medical field. In order to perform heart disease diagnosis an accurate and efficient automation system can be very helpful. In this research, we propose a classifier ensemble method to improve the decision of the classifiers for heart disease diagnosis. Homogeneous ensemble is applied for heart disease classification and finally results are optimized by using Genetic algorithm. Data is evaluated by using 10-fold cross validation and performance of the system is evaluated by classifiers accuracy, sensitivity and specificity to check the feasibility of our system. Comparison of our methodology with existing ensemble technique has shown considerable improvements in terms of classification accuracy.

Bison remains from the Upper Siwaliks of Pakistan

Fossil remains ascribed to Bison cf. sivalensis are described in this paper. The material, discovered by the team of Palaeontology of the Punjab University, Lahore, Pakistan during the past few years comes from the Early – Middle Pliocene continental deposits of the Upper Siwaliks (Tatrot Formation, northern Pakistan) dated approximately from 3.3 to 2.6 Ma, and allows interesting comparisons with forms related to the origin of bisons. The new data significantly widens the timedistribution of the species and draws back the first appearance of Bison lineage in the Indian subcontinent.

A Novel Fuzzy Logic Based Software Component Selection Modeling

Software component selection is the most important part of component based software development. A large amount of time is invested in searching and selecting the most appropriate component from component repository. Different methods are used to select components quickly and efficiently. In the proposed method we have used part of off the shelf option and fuzzy logic methodology for components selection. The proposed methodology incorporates several important factors such as efficiency, reusability, portability, functionality, security, testability and maintenance. The methodology is illustrated and evaluated using hypothetical case study.

Entamoeba infections in different populations of dogs in an endemic area of Lahore, Pakistan.

Entamoeba histolytica, a protozoan parasite that affects humans and other primates all over the world. It is a common waterborne pathogen in endemic areas that have fecal oral transmission cycle. The aim of the present study was to examine the prevalence of E. histolytica and other Entamoeba species cysts in three different dog populations. Fecal samples from 600 dogs were collected and processed to detect Entamoeba cysts using the triple fecal test (light microscopy) and fecal antigens of E. histolytica were detected using a fecal antigen ELISA (TechLab E. histolytica II). Because it is impossible to differentiate E. histolytica from Entamoeba dispar and E. moshkovskii, using light microscopy we referred to all cysts morphologically consistent with E. histolytica as E. histolytica/dispar/moskovskii to reflect this uncertainty. Samples from 197 household dogs without clinical signs, 122 samples from household dogs exhibiting clinical signs of diarrhea, dysentery and vomiting and 281 stray dogs with no specific clinical signs were examined. Entamoeba histolytica-like cysts were observed in 94 (15.6%, 95% CI=±3.88) by triple fecal test microscopy and E. histolytica antigens were demonstrated in 66 (11%, 95% CI=±4.41) by fecal antigen ELISA in 600 fecal samples. Significant differences (P≤0.05) in prevalence were found between the three populations. Twenty (10.1%, 95% CI=±7.86) and 11 (5.6%, 95% CI=±7.70) of 197 fecal samples from household dogs without clinical signs were positive by microscopy and by antigen ELISA, respectively. Twenty-nine (23.8%, 95% CI=±6.58) and 23 (18.8%, 95% CI=±7.81) of 122 the fecal samples from household dogs with clinical signs were positive by microscopy and by antigen ELISA, respectively. Forty-five (16.01%, 95% CI=±5.62) and 32 (11.3%, 95% CI=±6.38) of 281 fecal samples from stray dogs were positive by microscopy and by fecal antigen ELISA, respectively. Dogs from the youngest age group (6 months to 1 year) were more likely to be E. histolytica antigen positive than were dogs from the other two older age groups, with a significant difference (P≤0.05) between all age groups. Statistically, no significant (P≥0.05) difference of prevalence was seen in male and female dogs. The local dogs had the highest prevalence rate of E. histolytica antigens (36 of 246, 14.2%, 95% CI=±6.32) followed by imported breeds (11 of 115, 9.5%, 95% CI=±10.4) and crossbred (19 of 239, 8.3%, 95% CI=±7.47), indicating a significant (P≤0.05) trend of positivity between various breeds of dogs. These findings suggest that dogs may play an important role in the epidemiology of this pathogen.

Efficient gender classification methodology using DWT and PCA

Recognition of gender from face images has accomplished great popularity and also enlightened some new research problems. In this paper, we presented a new technique for gender classification using DWT and PCA. The technique has shown performance better than existing gender classification techniques. Experiments were carried out on standard face database used in various existing works of literature. Our proposed method provides high accuracy and is resilient to brightness changes comparison to those techniques which are in practice.

Modified Histogram Based Fuzzy Filter

In this paper, a fuzzy based impulse noise removal technique has been proposed. The proposed filter is based on noise detection, fuzzy set construction, histogram estimation and fuzzy filtering process. Noise detection process is used to identify the set of noisy pixels which are used for estimating the histogram of the original image. Estimated histogram of the original image is used for fuzzy set construction using fuzzy number construction algorithm. Fuzzy filtering process is the main component of the proposed technique. It consists of fuzzification, defuzzification and predicted intensity processes to remove impulse noise. Sensitivity analysis of the proposed technique has been performed by varying the number of fuzzy sets. Experimental results demonstrate that the proposed technique achieves much better performance than state-of-the-art filters. The comparison of the results is based on global error measure as well as local error measures i.e. mean square error (MSE) and structural similarity index measure (SSIM).

Prevalence of Entamoeba histolytica-Like Cysts Compared to E. histolytica Antigens Detected by ELISA in the Stools of 600 Patients from Three Socioeconomic Communities in the Metropolitan City of Lahore, Pakistan

Abstract:  Amoebiasis, caused by Entamoeba histolytica, has a worldwide distribution and is of public health significance in many developing countries. It has a fecal–oral transmission cycle and is most prevalent in developing countries in regions where substandard sanitary conditions exist due to poverty. Little is known about the epidemiology of E. histolytica infection and its presence in different socioeconomic communities in developing countries. We undertook the present study in the city of Lahore, Pakistan, and our prediction was that the prevalence of E. histolytica-like cysts and E. histolytica stool antigen would be lower in patients from upper socioeconomic levels than in individuals from middle or lower socioeconomic levels. We investigated the prevalence of E. histolytica in humans from 3 socioeconomic communities in territories of Lahore, Pakistan. Six hundred fecal samples were collected and examined using both microscopy (triple fecal test) to detect cysts of E. histolytica-like amoeba and ELISA (stool antigen ELISA) to demonstrate diagnostic stool antigens of E. histolytica. Samples were from individuals living under conditions deemed to be upper socioeconomic class (n = 287), middle socioeconomic class (n = 172), and lower socioeconomic class (n = 141). The total prevalence of positive samples was 22.5% (135/600) by triple test and 16.8% (101/600) by stool antigen ELISA in the 600 fecal samples. Statistically, significant (P < 0.05) differences in prevalence were seen between the 3 socioeconomic class groups. Forty-four (15.3%) and 32 (11.1%) of 287 in the fecal samples from the upper socioeconomic class were positive by triple test and by antigen ELISA, respectively. Thirty-nine (22.6%) and 29 (16.8%) of 172 in the fecal samples from the middle socioeconomic class were positive by the triple test and by antigen ELISA, respectively. Fifty-two (36.8%) and 40 (28.3%) of 141 in the fecal samples from the lower socioeconomic class were positive by the triple test and by antigen ELISA, respectively. We accept our hypothesis based on these findings. We also demonstrated that fecal samples collected from the youngest age group (1 mo–5 yr) were more likely to be positive for E. histolytica antigens than were samples from the other 3 age groups, and that prevalence was significantly higher (P < 0.05) in the summer than in the other 3 seasons. These results highlight the importance of surveillance of this relatively ignored pathogen in this developing metropolitan city in Pakistan.

Evaluating Security of Software Components Using Analytic Network Process

Increasing use of Component Based Software Engineering (CBSE) has raised the issues related with the security of software components. Several methodologies are being used to evaluate security of software components and that of the base system with which it is integrated. Security characteristics of a component must be specified effectively and unambiguously. To make possible software development progression, it will be effective to have a method which evaluates the security of software components. The study presented here attempts to propose analytic network process (ANP) for component security evaluation. The method is applied using ISO/IEC 27002 (ISO 27002) standard.

Fuzzy clustering and fuzzy entropy based classification model

In Pattern recognition, ensembles of classifiers are used to increase the performance and accuracy of classification systems. The creation of ensembles, selection of base classifiers and combining the decisions of the classifiers is an active research area. In this paper we propose a method of ensemble creation that is based on fuzzy clustering (Fuzzy C Mean) and fuzzy entropy; and named as Fuzzy Clustering and Fuzzy Entropy (FCFE) based classification model. With the help of FCM we obtained fuzzy membership matrix, revealing the underlying distribution and structure of the data. The Fuzzy entropy tells us about the degree of difficulty of classification of data. This information is used in sampling the training data into core sample and boundary sample. This sampling approach induces diversity in the ensemble which contributes to higher classification accuracy. The proposed method is evaluated on 4 UCI benchmark data sets with support vector machine (SVM) as the base classifier. The decision is combined using mean combiner rule. The results show that the proposed method delivers higher classification accuracy than stand alone SVM and the well known ensembles techniques of Bagging and Boosting.