Feature selection techniques are searching for an optimal subset of features required in the machine learning algorithms. Techniques like the statistical models have been applied for measuring the correlation degree for each feature separately. However, the mutual correlation and effect between features is not taken into consideration. The proposed technique measures the constructive and the destructive effect (gain) of adding a feature to a subset of features. This technique studies feature-feature correlation in addition to the feature-class label correlation. The optimality in the resulted subset of features is based on searching for a highly constructive subset of features with respect to the target class label. The proposed feature selection technique is tested by measuring the classification accuracy results of a data set containing subsets of constructively correlated features. A comparative analysis shows that the resulted classification accuracy and number of the selected feature of the proposed technique is better than the other feature selection techniques.
{"title":"Positive and Negative Feature-Feature Correlation Measure: AddGain","authors":"M. Salama, Ghada Hassan","doi":"10.1145/3220267.3220270","DOIUrl":"https://doi.org/10.1145/3220267.3220270","url":null,"abstract":"Feature selection techniques are searching for an optimal subset of features required in the machine learning algorithms. Techniques like the statistical models have been applied for measuring the correlation degree for each feature separately. However, the mutual correlation and effect between features is not taken into consideration. The proposed technique measures the constructive and the destructive effect (gain) of adding a feature to a subset of features. This technique studies feature-feature correlation in addition to the feature-class label correlation. The optimality in the resulted subset of features is based on searching for a highly constructive subset of features with respect to the target class label. The proposed feature selection technique is tested by measuring the classification accuracy results of a data set containing subsets of constructively correlated features. A comparative analysis shows that the resulted classification accuracy and number of the selected feature of the proposed technique is better than the other feature selection techniques.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126167660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Several applications have problems with the representation of the real numbers because of its drawbacks like the propagation and the accumulation of errors. These numbers have a fixed length format representation that provides a large dynamic range, but on the other hand it causes truncation of some parts of the numbers in case of a number that needs to be represented by a long stream of bits. Researchers suggested many solutions for these errors, one of these solutions is the Multi-Number (MN) system. MN system represents the real number as a vector of floating-point numbers with controlled accuracy by adjusting the length of the vector to accumulate the non-overlapping real number sequences. MN system main drawback is the MN computations that are iterative and time consuming, making it unsuitable for real time applications. In this work, the Single Instruction Multiple Data (SIMD) model supported in modern CPUs is exploited to accelerate the MN Computations. The basic arithmetic operation algorithms had been adjusted to make use of the SIMD architecture and support both single and double precision operations. The new architecture maintains the same accuracy of the original one, when was implemented for both single and double precision. Also, in this paper the normal Gaussian Jordan Elimination algorithm was proposed and used to get the inverse of the Hilbert Matrix, as an example of ill-conditioned matrices, instead of using iterative and time-consuming methods. The accuracy of the operations was proved by getting the inverse of the Hilbert Matrix and verify that the multiplication of the inverse and the original matrix producing the unity matrix. Hilbert Matrix inverse execution time was accelerated and achieved a speedup 3x, compared to the original NM operations. In addition to the previous, the accelerated MN system version was used to solve the polynomial regression problem.
{"title":"Efficient Architecture for Controlled Accurate Computation using AVX","authors":"DiaaEldin M. Osman, M. Sobh, A. Eldin, A. M. Zaki","doi":"10.1145/3220267.3220292","DOIUrl":"https://doi.org/10.1145/3220267.3220292","url":null,"abstract":"Several applications have problems with the representation of the real numbers because of its drawbacks like the propagation and the accumulation of errors. These numbers have a fixed length format representation that provides a large dynamic range, but on the other hand it causes truncation of some parts of the numbers in case of a number that needs to be represented by a long stream of bits. Researchers suggested many solutions for these errors, one of these solutions is the Multi-Number (MN) system. MN system represents the real number as a vector of floating-point numbers with controlled accuracy by adjusting the length of the vector to accumulate the non-overlapping real number sequences. MN system main drawback is the MN computations that are iterative and time consuming, making it unsuitable for real time applications. In this work, the Single Instruction Multiple Data (SIMD) model supported in modern CPUs is exploited to accelerate the MN Computations. The basic arithmetic operation algorithms had been adjusted to make use of the SIMD architecture and support both single and double precision operations. The new architecture maintains the same accuracy of the original one, when was implemented for both single and double precision. Also, in this paper the normal Gaussian Jordan Elimination algorithm was proposed and used to get the inverse of the Hilbert Matrix, as an example of ill-conditioned matrices, instead of using iterative and time-consuming methods. The accuracy of the operations was proved by getting the inverse of the Hilbert Matrix and verify that the multiplication of the inverse and the original matrix producing the unity matrix. Hilbert Matrix inverse execution time was accelerated and achieved a speedup 3x, compared to the original NM operations. In addition to the previous, the accelerated MN system version was used to solve the polynomial regression problem.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126757725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fuzzing is a widely used technology to find vulnerabilities, but the current technology is mostly based on coverage and there are relatively few research in the field of directed fuzzing. In this paper, a parallelized testing technique combining directed fuzzing and concolic execution will be proposed. It extracts path space within the level of basic block in the function call chain through the program control flow analysis and function call relationship. Concolic execution is used to implement the target reachable paths guidance, in order to achieve the goal of rapid arrival. In the experimental stage, the developed Directer was used to test on LAVA dataset, which shows better performance than the existing fuzzers.
{"title":"Directer: A Parallel and Directed Fuzzing based on Concolic Execution","authors":"Xiaobin Song, Zehui Wu, Yunchao Wang","doi":"10.1145/3220267.3220272","DOIUrl":"https://doi.org/10.1145/3220267.3220272","url":null,"abstract":"Fuzzing is a widely used technology to find vulnerabilities, but the current technology is mostly based on coverage and there are relatively few research in the field of directed fuzzing. In this paper, a parallelized testing technique combining directed fuzzing and concolic execution will be proposed. It extracts path space within the level of basic block in the function call chain through the program control flow analysis and function call relationship. Concolic execution is used to implement the target reachable paths guidance, in order to achieve the goal of rapid arrival. In the experimental stage, the developed Directer was used to test on LAVA dataset, which shows better performance than the existing fuzzers.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129804189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Low-dose computed tomography (LDCT) imaging is considerably recommended for use in clinical CT scanning because of growing fears over excessive radiation exposure. Automatic exposure control (AEC) is one of the methods used in dose reduction techniques that have been implemented clinically comprise showing significant decrease scan range. The quality of some images may be roughly degraded with noise and streak artifacts due to x-ray flux, based on modulating radiation dose in the angular and slice directions. In 2005, the nonlocal means (NLM) algorithm showed high performance in denoising images corrupted by LDCT. The proposed method incorporates a prior knowledge obtained from previous high-quality CT slices to improve low-quality CT slice during the filtering process because of the anatomical similarity between the arranged image slices of the scans. The proposed method is evaluated using real data and CT image quality is notably improved.
{"title":"Image Denoising Technique for CT Dose Modulation","authors":"Haneen A. Elyamani, S. El-Seoud, E. Rashed","doi":"10.1145/3220267.3220288","DOIUrl":"https://doi.org/10.1145/3220267.3220288","url":null,"abstract":"Low-dose computed tomography (LDCT) imaging is considerably recommended for use in clinical CT scanning because of growing fears over excessive radiation exposure. Automatic exposure control (AEC) is one of the methods used in dose reduction techniques that have been implemented clinically comprise showing significant decrease scan range. The quality of some images may be roughly degraded with noise and streak artifacts due to x-ray flux, based on modulating radiation dose in the angular and slice directions. In 2005, the nonlocal means (NLM) algorithm showed high performance in denoising images corrupted by LDCT. The proposed method incorporates a prior knowledge obtained from previous high-quality CT slices to improve low-quality CT slice during the filtering process because of the anatomical similarity between the arranged image slices of the scans. The proposed method is evaluated using real data and CT image quality is notably improved.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125435260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Automatic machine translation becomes an important source of translation nowadays. It is a software system that translates a text from one natural language to one (many) natural language. On the web, there are many machine translation systems that give the reasonable translation, although the systems are not very good. Medical records contain complex information that must be translated correctly according to its medical meaning not its English meaning only. So, the quality of a machine translation in this domain is very important. In this paper, we present using matching stage from Example-Based Machine Translation technique to translate a medical text from English as source language to Arabic as the target language. We have used 259 medical sentences that are extracted from internal medicine publications for our system. Experimental results on BLUE metrics showed a decreased performance 0.486 comparing to GOOGLE translation which has an accuracy result about 0.536.
{"title":"Example-Based English to Arabic Machine Translation: Matching Stage Using Internal Medicine Publications","authors":"R. Ehab, Eslam Amer, M. Gadallah","doi":"10.1145/3220267.3220294","DOIUrl":"https://doi.org/10.1145/3220267.3220294","url":null,"abstract":"Automatic machine translation becomes an important source of translation nowadays. It is a software system that translates a text from one natural language to one (many) natural language. On the web, there are many machine translation systems that give the reasonable translation, although the systems are not very good. Medical records contain complex information that must be translated correctly according to its medical meaning not its English meaning only. So, the quality of a machine translation in this domain is very important. In this paper, we present using matching stage from Example-Based Machine Translation technique to translate a medical text from English as source language to Arabic as the target language. We have used 259 medical sentences that are extracted from internal medicine publications for our system. Experimental results on BLUE metrics showed a decreased performance 0.486 comparing to GOOGLE translation which has an accuracy result about 0.536.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134054108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In Egypt, Traffic police or traffic officers usually write down the car license numbers and characters to enforce traffic rules. This is subject to errors of writing or reading the numbers and characters. The proposed work can utilise the advantage of widely spread of mobile phones. Officers can take pictures of car plate licenses and the system converts the pictures of car plate numbers and characters into digital numbers and letters. Arabic characters are challenging because some are very similar to each other's unlike the English characters.. For example, feh (ف) and Qaaf (ق), noon (ن) and ba (ب) difference is minor. The challenge of this work is to extract the Arabic characters and numbers with high accuracy from pictures of new and old car plate design and pictures by regular people. The algorithm has five steps image acquisition, pre-processing, segmentation, feature extraction, and character recognition. To improve the performance time, in the pre-processing step, the developed system tests the cropped area, converts the picture into gray scale, reverses color, and converts it into binary image. Then, it uses morphological operations which is dilation. To improve the accuracy, in the feature extraction step it uses SURF (Speeded Up Robust Features) and cross correlation algorithms in the character recognition. The system is tested with 21 plate pictures and the accuracy is 95% and only one plate picture was missed.
{"title":"Extraction of Egyptian License Plate Numbers and Characters Using SURF and Cross Correlation","authors":"A. Nosseir, Ramy Roshdy","doi":"10.1145/3220267.3220276","DOIUrl":"https://doi.org/10.1145/3220267.3220276","url":null,"abstract":"In Egypt, Traffic police or traffic officers usually write down the car license numbers and characters to enforce traffic rules. This is subject to errors of writing or reading the numbers and characters. The proposed work can utilise the advantage of widely spread of mobile phones. Officers can take pictures of car plate licenses and the system converts the pictures of car plate numbers and characters into digital numbers and letters. Arabic characters are challenging because some are very similar to each other's unlike the English characters.. For example, feh (ف) and Qaaf (ق), noon (ن) and ba (ب) difference is minor. The challenge of this work is to extract the Arabic characters and numbers with high accuracy from pictures of new and old car plate design and pictures by regular people.\u0000 The algorithm has five steps image acquisition, pre-processing, segmentation, feature extraction, and character recognition. To improve the performance time, in the pre-processing step, the developed system tests the cropped area, converts the picture into gray scale, reverses color, and converts it into binary image. Then, it uses morphological operations which is dilation. To improve the accuracy, in the feature extraction step it uses SURF (Speeded Up Robust Features) and cross correlation algorithms in the character recognition. The system is tested with 21 plate pictures and the accuracy is 95% and only one plate picture was missed.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131061168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
It is important to know the actual size and complexity of the software before predicting the amount of effort required to be implemented. Two most common methods used for software size estimation are: (i) Source Lines of Code (SLOC) and (ii) Function Point Analysis (FPA). Estimating the size of a software with SLOC method is only possible once the process of coding is completed. On the other hand, estimating software size with FPA method is possible in early phases of Software Development Life Cycle (SDLC). However, one main challenge from the viewpoint of software development phase, is the presence of inconsistent states of software artifacts i.e. some of the classes are completely developed, some are partially developed, and some are not developed yet. Therefore, this research is using the new developed model i.e. Function Point Analysis for Software Development Phase (FPA-SDP) in an empirical study to overcome this challenge. The results of FPA-SDP model can help software project managers in: (i) knowing the inconsistent states of software artifacts (ii) estimating the actual size of a change request with its complexity level for software development phase.
{"title":"An Empirical Study with Function Point Analysis for Software Development Phase Method","authors":"J. Shah, Nazri Kama, Saiful Adli Ismail","doi":"10.1145/3220267.3220268","DOIUrl":"https://doi.org/10.1145/3220267.3220268","url":null,"abstract":"It is important to know the actual size and complexity of the software before predicting the amount of effort required to be implemented. Two most common methods used for software size estimation are: (i) Source Lines of Code (SLOC) and (ii) Function Point Analysis (FPA). Estimating the size of a software with SLOC method is only possible once the process of coding is completed. On the other hand, estimating software size with FPA method is possible in early phases of Software Development Life Cycle (SDLC). However, one main challenge from the viewpoint of software development phase, is the presence of inconsistent states of software artifacts i.e. some of the classes are completely developed, some are partially developed, and some are not developed yet. Therefore, this research is using the new developed model i.e. Function Point Analysis for Software Development Phase (FPA-SDP) in an empirical study to overcome this challenge. The results of FPA-SDP model can help software project managers in: (i) knowing the inconsistent states of software artifacts (ii) estimating the actual size of a change request with its complexity level for software development phase.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127008520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
3D video call is a set of technologies, which allow a caller to feel the depth of the other caller and to give the real-life feeling. 3D video call is a developing technology that can be presented by peer-to-peer architecture. Cloud-based technologies are driving positive changes in the way organizations can communicate. In running a global business, the need for travel and being available in meetings is a must. However, with expensive travel costs, an alternative solution to overcome this problem is required. This paper presents, a new approach that enhances current 2D video calls to 3D video calls benefiting from the unlimited features of the cloud-computing. Three technologies were implemented, OpenStack cloud, webRTC call and 3D anaglyph effect to achieve the sense of 3D video.
{"title":"A New Approach for Implementing 3D Video Call on Cloud Computing Infrastructure","authors":"Nada Radwan, M. B. Abdelhalim, Ashraf AbdelRaouf","doi":"10.1145/3220267.3220274","DOIUrl":"https://doi.org/10.1145/3220267.3220274","url":null,"abstract":"3D video call is a set of technologies, which allow a caller to feel the depth of the other caller and to give the real-life feeling. 3D video call is a developing technology that can be presented by peer-to-peer architecture. Cloud-based technologies are driving positive changes in the way organizations can communicate. In running a global business, the need for travel and being available in meetings is a must. However, with expensive travel costs, an alternative solution to overcome this problem is required. This paper presents, a new approach that enhances current 2D video calls to 3D video calls benefiting from the unlimited features of the cloud-computing. Three technologies were implemented, OpenStack cloud, webRTC call and 3D anaglyph effect to achieve the sense of 3D video.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129152815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Reham Rabie, M. Eltoukhy, M. Al-Shatouri, E. Rashed
This work introduces a computer-aided diagnosis (CAD) system for diagnosing liver cirrhosis in ultrasound (US) images. The proposed system uses a set of features obtained from different feature extraction methods. These features are the first order statistics (FOS), the fractal dimension (FD), the gray level co-occurrence matrix (GLCM), the Gabor filter (GF), the wavelet (WT) and the curvelet (CT) features. The measured features are presented in two different classifiers such as support vector machine (SVM) and k-nearest neighbors (K-NN). The proposed system is applied on dataset consists of 72 cirrhosis and 75 normal regions each of 128x128 pixels. The classification accuracy rates are calculated using a 10-fold cross validation. A correlation-based feature selection (CFS) is used resulting in better accuracy predictions. The results showed that SVM and K-NN classifiers achieved higher performance with the combination of the wavelet and curvelet feature vectors than other feature extraction methods.
{"title":"Computer Aided Diagnosis System for Liver Cirrhosis Based on Ultrasound Images","authors":"Reham Rabie, M. Eltoukhy, M. Al-Shatouri, E. Rashed","doi":"10.1145/3220267.3220283","DOIUrl":"https://doi.org/10.1145/3220267.3220283","url":null,"abstract":"This work introduces a computer-aided diagnosis (CAD) system for diagnosing liver cirrhosis in ultrasound (US) images. The proposed system uses a set of features obtained from different feature extraction methods. These features are the first order statistics (FOS), the fractal dimension (FD), the gray level co-occurrence matrix (GLCM), the Gabor filter (GF), the wavelet (WT) and the curvelet (CT) features. The measured features are presented in two different classifiers such as support vector machine (SVM) and k-nearest neighbors (K-NN). The proposed system is applied on dataset consists of 72 cirrhosis and 75 normal regions each of 128x128 pixels. The classification accuracy rates are calculated using a 10-fold cross validation. A correlation-based feature selection (CFS) is used resulting in better accuracy predictions. The results showed that SVM and K-NN classifiers achieved higher performance with the combination of the wavelet and curvelet feature vectors than other feature extraction methods.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"319 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122315646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nowadays, there are a lot of classifications models used for predictions in the software engineering field such as effort estimation and defect prediction. One of these models is the ensemble learning machine that improves model performance by combining multiple models in different ways to get a more powerful model. One of the problems facing the prediction model is the misclassification of the minority samples. This problem mainly appears in the case of defect prediction. Our aim is the classification of defects which are considered minority samples during the training phase. This can be improved by implementing the Synthetic Minority Over-Sampling Technique (SMOTE) before the implementation of the ensemble model which leads to over-sample the minority class instances. In this paper, our work propose applying a new ensemble model by combining the SMOTE technique with the heterogeneous stacking ensemble to get the most benefit and performance in training a dataset that focus on the minority subset as in the software prediction study. Our proposed model shows better performance that overcomes other techniques results applied on the minority samples of the defect prediction.
{"title":"Using SMOTE and Heterogeneous Stacking in Ensemble learning for Software Defect Prediction","authors":"S. El-Shorbagy, Wael El-Gammal, W. Abdelmoez","doi":"10.1145/3220267.3220286","DOIUrl":"https://doi.org/10.1145/3220267.3220286","url":null,"abstract":"Nowadays, there are a lot of classifications models used for predictions in the software engineering field such as effort estimation and defect prediction. One of these models is the ensemble learning machine that improves model performance by combining multiple models in different ways to get a more powerful model.\u0000 One of the problems facing the prediction model is the misclassification of the minority samples. This problem mainly appears in the case of defect prediction. Our aim is the classification of defects which are considered minority samples during the training phase. This can be improved by implementing the Synthetic Minority Over-Sampling Technique (SMOTE) before the implementation of the ensemble model which leads to over-sample the minority class instances.\u0000 In this paper, our work propose applying a new ensemble model by combining the SMOTE technique with the heterogeneous stacking ensemble to get the most benefit and performance in training a dataset that focus on the minority subset as in the software prediction study. Our proposed model shows better performance that overcomes other techniques results applied on the minority samples of the defect prediction.","PeriodicalId":177522,"journal":{"name":"International Conference on Software and Information Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129966269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：