نشریه محاسبات نرم
سال پنجم شماره 2 (پیاپی 10، پاییز و زمستان 1395)

The impacts of employing healthcare information systems in decreasing the admission and discharge time, patient transfer time, the internal clashes and clinical applications, time to get answers and refer to previous data file, increasing information and request accuracy, accelerating the communication between hospital wards, increasing patient satisfaction, providing better quality services, accessing hospital income and expenses information, downsizing, etc. are obvious in recent decade. Regarding the significance and the broad application of these softwares, there are a few number of research to verify their conformance as a whole or a collection of components with software quality metrics. In this research, the quality of healthcare information systems componets that are currently being used in hospitals in Guilan province is investigated regarding their conformance to software technical quality metrics. To this end, ten components of five healthcare information systems are analyzed with gathering information of users through questionnaire. The conformance degree of each component with software quality metrics is statistically analyzed and presented through this paper.

After vehicle detection and vehicle type recognition, it is vehicle make and model recognition (VMMR) that has attracted researchers attention in the last decade. Due to the large number of classes and small inner-class distance, this problem is known as a hard classification problem.
In this paper, a comparison between holistic and part-based approaches has been made and most of the previous methods in each category have been reviewed. In addition, a new part-based method is proposed which tries to overcome some of the hard challenges in this area. This method operates on meaningful parts of vehicle like lights, grilles and logo for distinguishing of different classes. The Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) have been used for feature extraction and classification tasks respectively. For evaluation purposes, a dataset including 352 images from frontal and rear view of eight different classes of vehicles have been prepared and fully marked based on their parts. The experimental results show the effectiveness of the proposed part-based approach in comparison to the traditional approaches. The proposed method achieved 95.4% accuracy on frontal view and 100% accuracy on rear view images.

Let G=(V,E) be a graph where v(G) and E(G) are vertices and edges of G, respectively. Sum of distance between vertices of graphs is called wiener invariant. In This paper, we present some proved results on the wiener invariant and some new result on the upper bound of wiener invariant of k-connected graphs.

According to the studies carried out in recent years, determination of the regional proposal is one of the crucial steps in detection and recognition of the objects included in an image. In fact, determination of this region has been like a bottleneck, gaining a significant computational energy. As a result, selection of suitable and fast approaches, under these circumstance, may enhance the performance of the recognition system. In this paper, a review was provided on the recent studies carried out in this field of research and few of the famous and friendly approaches conventionally used in the strong recognition systems were introduced and applied on the dataset of PASCAL VOC, ImageNet and COCO. The results obtained indicated that the multiclass combinatorial grouping (MCG) method with the region-convoulational neural network (R-CNN) can provide the best results with the efficiency of 57%, 54% and 41% on the dataset of PASCAL VOC 2007, ImageNet 2013 and COCO 2014 respectively.

Prediction of urban air pollution is an important subject in environmental studies. However, the required data for prediction is not available for every interested location. So, different models have been proposed for air pollution prediction. The feature selection (among 20 features given in Meteorology Organization data) was performed by binary gravitational search algorithm (BGSA) in this study and 10 features were selected. An artificial neural network (ANN) was used in this study for air pollution prediction. This ANN was trained using chaotic gravitational search algorithm (CGSA). In a comparative study, the performance evaluation of this neural predictor was performed when other methods were also used for ANN training. These methods were error back propagation, standard GSA, artificial bee colony, particle swarm optimization, and hybrid of genetic algorithm and simulated annealing. Experimental results showed the superior performance of the proposed BGSA-CGSA method used for feature selection and ANN training.

Froth flotation is the most widely used technique for the separation of valuable minerals from gangue ones. Changeable nature of feed, interaction of variables and weakness of accurate measurement equipment have made the development of monitoring methods and continues control of flotation circuits to an important issue. Today with the advance of technology, machine vision systems based on image processing methods are considered a rapid, cheap and safe detection device in mineral processing industries. The appearance of flotation froth surface consists of significant information process which easily distinguishes the process operation condition. Size distribution of froth bubbles is the reflection of froth stability and velocity and is the best criterion for the efficiency estimation of flotation operation. This paper is the updated review of the most common methods of size estimation of flotation froth bubbles along with their benefits and shortcomings and ideas for future studies in this area. Likewise, the correlation between concentrate grade and recovery with the froth bubble size is investigated.