Locally weighted regression with different kernel smoothers for software effort estimation
Authors : Yousef Alqasrawi,Mohammad Azzeh,Yousef Elsheikh
Abstract : Estimating software effort has been a largely unsolved problem for decades. One of the main reasons that hinders building accurate estimation models is the often heterogeneous nature of software data with a complex structure. Typically, building effort estimation models from local data tends to be more accurate than using the entire data. Previous studies have focused on the use of clustering techniques and decision trees to generate local and coherent data that can help in building local prediction models. However, these approaches may fall short in some aspect due to limitations in finding optimal clusters and processing noisy data. In this paper we used a more sophisticated locality approach that can mitigate these shortcomings that is Locally Weighted Regression (LWR). This method provides an efficient solution to learn from local data by building an estimation model that combines multiple local regression models in k-nearest-neighbor based model. The main factor affecting the accuracy of this method is the choice of the kernel function used to derive the weights for local regression models. This paper investigates the effects of choosing different kernels on the performance of Locally Weighted Regression of a software effort estimation problem. After comprehensive experiments with 7 datasets, 10 kernels, 3 polynomial degrees and 4 bandwidth values with a total of 840 Locally Weighted Regression variants, we found that: 1) Uniform kernel functions cannot outperform non-uniform kernel functions, and 2) kernel type, polynomial degrees and bandwidth parameters have no specific effect on the estimation accuracy. In other words, no change in bandwidth or degree values occurred with a significant difference in kernel rankings. In short, Locally Weighted Regression methods with Triweight or Triangle kernel can perform better than more complex kernels. Hence, we encourage non-uniform kernel methods as smoother function with wide bandwidth and small polynomial degree
Keywords : Effort estimation, Locally weighted regression, Kernel function, k-nearest neighbors
رابط البحث
On obtaining a stable vote ranking methodology for implementing e-government strategies
Authors : Yousef Alqasrawi,Mohammad Azzeh,Yousef Elsheikh
Abstract : Recently, a lot of studies have been conducted on what factors and strategies affect the successful implementation of e-government programs around the world. Most of these studies lack a clear plan for selecting strategies and setting their priorities for implementation and thus ensuring the success of such programs. In a previous study conducted by the same researchers, these strategies and their implementation priorities were defined based on the opinions of 20 government experts who were interviewed and asked to rank the strategies based on 23 factors resulting from the SWOT analysis that summarizes the context under study, specifically Jordan as an example of a developing country. However, there is a problem that still exists facing many of these countries, which is the divergence of opinions of government decision-makers in ranking their priorities for implementing various government strategies, including e-government programs, and thus affecting the quality of the strategic decision taken. Therefore, this study will address the problem by finding a new methodology that enables to obtain a stable ranking of strategies in order to make the best strategic decision to implement the e-government program in the context under study or other similar contexts in the region. This study assumes that we can obtain a stable ranking of strategies related to implementing e-government programs when we only use the SWOT factors that produce stable ranking votes. To validate this, three main experiments with a number of proposed scenarios were developed to aggregate expert rankings on the implementation of e-government strategies using some common vote ranking methods, namely, parametric methods such as Borda, Copeland and Maximin, and algorithmic methods such as Stuart and Robust Rank Aggregation (RRA). Then, to evaluate the results of the three experimental scenarios, two new measures were proposed, namely the Similarity Index measure and the Matching Index measure. The results confirmed the validity of the assumption regarding the importance of obtaining a stable vote ranking in selecting the best strategies to ensure success in implementing e-government program in the context under study or other similar contexts in the region.
Keywords : SWOT analysis, Alternative strategies, Ranked voting theory, E-government, Developing world, Jordan
رابط البحث
Bridging the gap between local semantic concepts and bag of visual words for natural scene image retrieval
Authors : Yousef Alqasrawi
Abstract : Background: A typical content-based image retrieval system deals with the query image and images in the dataset as a collection of low-level features and retrieves a ranked list of images based on the similarities between features of the query image and features of images in the image dataset. However, top ranked images in the retrieved list, which have high similarities to the query image, may be different from the query image in terms of the semantic interpretation of the user which is known as the semantic gap. In order to reduce the semantic gap, this paper investigates how natural scene retrieval can be performed using the bag of visual word model and the distribution of local semantic concepts. Methods: We study the efficiency of using different approaches for representing the semantic information, depicted in natural scene images, for image retrieval. Results: The semantic representation of the natural scene images has been implemented using the annotated and un-annotated images. Firstly, the retrieval performance when employing the COV to summarize the amount of local semantic concepts depicted in an image have reported an encouraging results. The COV constructed from the labels of image regions represented by the BOW model have shown better performance compared with the baseline methods, such as color histogram, and also comparable with the COV benchmark. Secondly, the retrieval performance of using different configuration of the bag of visual word model have been studied and evaluated experimentally using three natural scene datasets. Conclusion: The experimental results obtained using the different image datasets have shown that the concept occurrence vector approaches achieved better retrieval accuracy compared to the BOW-based approaches and baseline.
Keywords : Image retrieval, natural scenes, bag of visual words, visual vocabulary, low-level features, local semantic concepts.
رابط البحث
Natural scene image annotation using local semantic concepts and spatial bag of visual words
Authors : Yousef Alqasrawi
Abstract : Background: Most techniques that adopt the BOW model in annotating im-ages declined favorable information that can be mined from image categories to build discriminative visual vocabularies. We introduce a detailed framework for automatically annotating natural scene images with local semantic labels from a predefined vocabulary. Methods: The proposed framework is based on a hypothesis that assumes that, in natural scenes, intermediate semantic concepts are correlated with the local keypoints. Based on this hypothesis, image regions can be efficiently represented by BOW model and using a machine learning approach, such as SVM, to label image regions with semantic annotations. Another objective of this paper is to address the implications of generating visual vocabularies from image halves, instead of producing them from the whole image, on the performance of annotating im-age regions with semantic labels. Results: The reported results have shown the plausibility of using the BOW model to represent the semantic information of image regions and thus to automatically annotate image regions with semantic labels. Conclusion: Our experimental results shows the plausibility of local from global approach for image region annotation as well as the discriminative power of using visual vocabularies from image halves. It showed an improved annotation results using integrated bag of visual words combined with low-level features.
Keywords : Image annotation, natural scenes, bag of visual words, visual vocabulary, semantic modelling, semantic concepts.
رابط البحث
Investigating the relationship between the distribution of local semantic concepts and local keypoints for image annotation
Authors : Yousef Alqasrawi, Daniel Neagu
Abstract : The problem of image annotation has gained increasing attention from many researchers in computer vision. Few works have addressed the use of bag of visual words for scene annotation at region level. The aim of this paper is to study the relationship between the distribution of local semantic concepts and local keypoints located in image regions labelled with these semantic concepts. Based on this study, we investigate whether bag of visual words model can be used to efficiently represent the content of natural scene image regions, so images can be annotated with local semantic concepts. Also, this paper presents local from global approach which study the influence of using visual vocabularies generated from general scene categories to build bag of visual words at region level. Extensive experiments are conducted over a natural scene dataset with six categories. The reported results have shown the plausibility of using the BOW model to represent the semantic information of image regions.
Keywords : Visualization, Semantics, Vocabulary, Feature extraction, Histograms, Detectors, Correlation, scene image annotation, bag of visual words, semantic modelling, visual vocabulary, Concept-based Bag of Visual Words
رابط البحث
Fusing integrated visual vocabularies-based bag of visual words and weighted colour moments on spatial pyramid layout for natural scene image classification
Authors : Yousef Alqasrawi, Daniel Neagu, Peter I. Cowling
Abstract : The bag of visual words (BOW) model is an efficient image representation technique for image categorization and annotation tasks. Building good visual vocabularies, from automatically extracted image feature vectors, produces discriminative visual words, which can improve the accuracy of image categorization tasks. Most approaches that use the BOW model in categorizing images ignore useful information that can be obtained from image classes to build visual vocabularies. Moreover, most BOW models use intensity features extracted from local regions and disregard colour information, which is an important characteristic of any natural scene image. In this paper, we show that integrating visual vocabularies generated from each image category improves the BOW image representation and improves accuracy in natural scene image classification. We use a keypoint density-based weighting method to combine the BOW representation with image colour information on a spatial pyramid layout. In addition, we show that visual vocabularies generated from training images of one scene image dataset can plausibly represent another scene image dataset on the same domain. This helps in reducing time and effort needed to build new visual vocabularies. The proposed approach is evaluated over three well-known scene classification datasets with 6, 8 and 15 scene categories, respectively, using 10-fold cross-validation. The experimental results, using support vector machines with histogram intersection kernel, show that the proposed approach outperforms baseline methods such as Gist features, rgbSIFT features and different configurations of the BOW model.
Keywords : Image classification, Natural scenes, Bag of visual words, Integrated visual vocabulary, Pyramidal colour moments, Feature fusion, Semantic modelling
رابط البحث
Spatial pyramid local keypoints quantization for bag of visual patches image representation
Authors : Yousef Alqasrawi, Daniel Neagu, Peter I. Cowling
Abstract : Bag of visual patches (BOP) image representation has been the main research topic in computer vision literature for scene and object recognition tasks. Building visual vocabularies from local image feature vectors extracted automatically from images have direct effect on producing discriminative visual patches. Local image features hold important information of their locations in the image which are ignored during quantization process to build visual vocabularies. In this paper, we propose Spatial Pyramid Vocabulary Model (SPVM) to build visual vocabularies from local image features at pyramid level. We show, with experiments on multi-class classification task using 700 natural scene images, that the spatial pyramid vocabulary model is suitable and discriminative for bag-of-visual patches semantic image representation compared to using universal vocabulary model (UVM).
Keywords : Bag of visual patches, image classification, Pyramid visual vocabulary, semantic modelling
رابط البحث
Natural scene image recognition by fusing weighted colour moments with bag of visual patches on spatial pyramid layout
Authors : Yousef Alqasrawi, Daniel Neagu, Peter I. Cowling
Abstract : The problem of object/scene image classification has gained increasing attention from many researchers in computer vision. In this paper we investigate a number of early fusion methods using a novel approach to combine image colour information and the bag of visual patches (BOP) for recognizing natural scene image categories. We propose keypoints density-based weighting method (KDW) for merging colour moments and the BOP on a spatial pyramid layout. We found that the density of keypoints located in each image sub-region at specific granularity has noticeable impacts on deciding the importance of colour moments on that image sub-region. We demonstrate the validity of our approach on a six categories dataset of natural scene images. Experimental results have proved the effectiveness of our proposed approach.
Keywords : scene image classification, features fusion, semantic modelling
رابط البحث