In recent years, Deep neural networks (DNNs) have achieved great success in sequence modeling. Several deep models have been used for enhancing Handwriting Text Recognition (HTR). Among these models, Convolutional Neural Networks (CNNs) and Recurrent Neural network especially Long-Short-Term-Memory (LSTM) networks achieve state-of-the-art recognition accuracy. The recognition methods for Arabic text lines have been widely applied in many specific tasks. However, there are still some potential challenges as the lack of available and large Arabic text recognition dataset and the characteristics of Arabic script. In order to address these challenges, we propose an end-to-end recognition method based on convolutional recurrent neural networks (CRNNs), which adds feature reuse network component on the basis of a CRNN. The model is trained and tested on two Arabic text recognition datasets named KHATT and AHTID/MW. The experimental results demonstrate that the proposed method achieves better performance than other methods in the literature.
{"title":"Densely connected layer to improve VGGnet-based CRNN for Arabic handwriting text line recognition","authors":"Zouhaira Noubigh, Anis Mezghani, M. Kherallah","doi":"10.3233/his-210009","DOIUrl":"https://doi.org/10.3233/his-210009","url":null,"abstract":"In recent years, Deep neural networks (DNNs) have achieved great success in sequence modeling. Several deep models have been used for enhancing Handwriting Text Recognition (HTR). Among these models, Convolutional Neural Networks (CNNs) and Recurrent Neural network especially Long-Short-Term-Memory (LSTM) networks achieve state-of-the-art recognition accuracy. The recognition methods for Arabic text lines have been widely applied in many specific tasks. However, there are still some potential challenges as the lack of available and large Arabic text recognition dataset and the characteristics of Arabic script. In order to address these challenges, we propose an end-to-end recognition method based on convolutional recurrent neural networks (CRNNs), which adds feature reuse network component on the basis of a CRNN. The model is trained and tested on two Arabic text recognition datasets named KHATT and AHTID/MW. The experimental results demonstrate that the proposed method achieves better performance than other methods in the literature.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"64 1","pages":"113-127"},"PeriodicalIF":0.0,"publicationDate":"2021-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84831411","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}
Medical image techniques are used to examine and determine the well-being of the foetus during pregnancy. Digital image processing (DIP) is essential to extract valuable information embedded in most biomedical signals. Afterwords, intelligent segmentation methods, based on classifier algorithms, must be applied to identify structures and relevant features from previous data. The success of both is essential for helping doctors to identify adverse health conditions from the medical images. To obtain easy and reliable DIP methods for foetus images in real-time, at different gestational ages, aware pre-processing needs to be applied to the images. Thence, some data features are extracted that are meant to be used as input to the segmentation algorithms presented in this work. Due to the high dimension of the problems in question, assemblage of the data is also desired. The segmentation of the images is done by revisiting the K-nn algorithm that is a conventional nonparametric classifier. Besides its simplicity, its power to accomplish high classification results in medical applications has been demonstrated. In this work two versions of this algorithm are presented (i) an enhancement of the standard version by aggregating the data apriori and (ii) an iterative version of the same method where the training set (TS) is not static. The procedure is demonstrated in two experiments, where two images of different technologies were selected: a magnetic resonance image and an ultrasound image, respectively. The results were assessed by comparison with the K-means clustering algorithm, a well-known and robust method for this type of task. Both described versions showed results close to 100% matching with the ones obtained by the validation method, although the iterative version displays much higher reliability in the classification.
{"title":"Revisiting the K-nn algorithm for obstetric image segmentation","authors":"P. Salgado, T. Azevedo-Perdicoúlis","doi":"10.3233/HIS-210001","DOIUrl":"https://doi.org/10.3233/HIS-210001","url":null,"abstract":"Medical image techniques are used to examine and determine the well-being of the foetus during pregnancy. Digital image processing (DIP) is essential to extract valuable information embedded in most biomedical signals. Afterwords, intelligent segmentation methods, based on classifier algorithms, must be applied to identify structures and relevant features from previous data. The success of both is essential for helping doctors to identify adverse health conditions from the medical images. To obtain easy and reliable DIP methods for foetus images in real-time, at different gestational ages, aware pre-processing needs to be applied to the images. Thence, some data features are extracted that are meant to be used as input to the segmentation algorithms presented in this work. Due to the high dimension of the problems in question, assemblage of the data is also desired. The segmentation of the images is done by revisiting the K-nn algorithm that is a conventional nonparametric classifier. Besides its simplicity, its power to accomplish high classification results in medical applications has been demonstrated. In this work two versions of this algorithm are presented (i) an enhancement of the standard version by aggregating the data apriori and (ii) an iterative version of the same method where the training set (TS) is not static. The procedure is demonstrated in two experiments, where two images of different technologies were selected: a magnetic resonance image and an ultrasound image, respectively. The results were assessed by comparison with the K-means clustering algorithm, a well-known and robust method for this type of task. Both described versions showed results close to 100% matching with the ones obtained by the validation method, although the iterative version displays much higher reliability in the classification.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"12 1","pages":"1-13"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81794569","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}
U. Umoh, Imo J. Eyoh, V. Murugesan, A. Abayomi, S. Udoh
Healthcare systems need to overcome the high mortality rate associated with cardiovascular disease and improve patients’ health by using decision support models that are both quantitative and qualitative. However, existing models emphasize mathematical procedures, which are only good for analyzing quantitative decision variables and have failed to consider several relevant qualitative decision variables which cannot be simply quantified. In solving this problem, some models such as interval type-2 fuzzy logic (IT2FL) and flower pollination algorithm (FPA) have been used in isolation. IT2FL is a simplified version of T2FL, with a reduced computation complexity and additional design degrees of freedom, but it cannot naturally achieve the rules it uses in making decisions. FPA is a bio-inspired method based on the process of pollination, executed by the flowering plants, with the ability to learn, generalize and process numerous measurable data, but it is not able to describe how it reaches its decisions. The hybrid intelligent IT2FL-FPA system can conquer the constraints of individual approaches and strengthens their robustness to cope with healthcare data. This work develops a hybrid intelligent telemedical monitoring and predictive system using IT2FL and FPA. The main objective of this paper is to find the best membership functions (MFs) parameters of the IT2FL for an optimal solution. The FPA technique is employed to find the optimal parameters of the MFs used for IT2FLSs. The authors tested two data sets for the monitoring and prediction problems, namely: cardiovascular disease patients’ clinical and real-time datasets for shock-level monitoring and prediction.
{"title":"Hybrid intelligent telemedical monitoring and predictive systems","authors":"U. Umoh, Imo J. Eyoh, V. Murugesan, A. Abayomi, S. Udoh","doi":"10.3233/HIS-210005","DOIUrl":"https://doi.org/10.3233/HIS-210005","url":null,"abstract":"Healthcare systems need to overcome the high mortality rate associated with cardiovascular disease and improve patients’ health by using decision support models that are both quantitative and qualitative. However, existing models emphasize mathematical procedures, which are only good for analyzing quantitative decision variables and have failed to consider several relevant qualitative decision variables which cannot be simply quantified. In solving this problem, some models such as interval type-2 fuzzy logic (IT2FL) and flower pollination algorithm (FPA) have been used in isolation. IT2FL is a simplified version of T2FL, with a reduced computation complexity and additional design degrees of freedom, but it cannot naturally achieve the rules it uses in making decisions. FPA is a bio-inspired method based on the process of pollination, executed by the flowering plants, with the ability to learn, generalize and process numerous measurable data, but it is not able to describe how it reaches its decisions. The hybrid intelligent IT2FL-FPA system can conquer the constraints of individual approaches and strengthens their robustness to cope with healthcare data. This work develops a hybrid intelligent telemedical monitoring and predictive system using IT2FL and FPA. The main objective of this paper is to find the best membership functions (MFs) parameters of the IT2FL for an optimal solution. The FPA technique is employed to find the optimal parameters of the MFs used for IT2FLSs. The authors tested two data sets for the monitoring and prediction problems, namely: cardiovascular disease patients’ clinical and real-time datasets for shock-level monitoring and prediction.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"11 1","pages":"43-57"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89456563","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}
Subrato Bharati, Prajoy Podder, M. Mondal, V. B. Surya Prasath
This paper focuses on the application of deep learning (DL) based model in the analysis of novel coronavirus disease (COVID-19) from X-ray images. The novelty of this work is in the development of a new DL algorithm termed as optimized residual network (CO-ResNet) for COVID-19. The proposed CO-ResNet is developed by applying hyperparameter tuning to the conventional ResNet 101. CO-ResNet is applied to a novel dataset of 5,935 X-ray images retrieved from two publicly available datasets. By utilizing resizing, augmentation and normalization and testing different epochs our CO-ResNet was optimized for detecting COVID-19 versus pneumonia with normal healthy lung controls. Different evaluation metrics such as the classification accuracy, F1 score, recall, precision, area under the receiver operating characteristics curve (AUC) are used. Our proposed CO-ResNet obtains consistently best performance in the multi-level data classification problem, including health lung, pneumonia affected lung and COVID-19 affected lung samples. In the experimental evaluation, the detection rate accuracy in discerning COVID-19 is 98.74%, and for healthy normal lungs, pneumonia affected lungs are 92.08% and 91.32% respectively for our CO-ResNet with ResNet101 backbone. Further, our model obtained accuracy values of 83.68% and 82% for healthy normal lungs and pneumonia affected lungs with ResNet152 backbone. Experimental results indicate the potential usage of our new DL driven model for classification of COVID-19 and pneumonia.
{"title":"CO-ResNet: Optimized ResNet model for COVID-19 diagnosis from X-ray images","authors":"Subrato Bharati, Prajoy Podder, M. Mondal, V. B. Surya Prasath","doi":"10.3233/HIS-210008","DOIUrl":"https://doi.org/10.3233/HIS-210008","url":null,"abstract":"This paper focuses on the application of deep learning (DL) based model in the analysis of novel coronavirus disease (COVID-19) from X-ray images. The novelty of this work is in the development of a new DL algorithm termed as optimized residual network (CO-ResNet) for COVID-19. The proposed CO-ResNet is developed by applying hyperparameter tuning to the conventional ResNet 101. CO-ResNet is applied to a novel dataset of 5,935 X-ray images retrieved from two publicly available datasets. By utilizing resizing, augmentation and normalization and testing different epochs our CO-ResNet was optimized for detecting COVID-19 versus pneumonia with normal healthy lung controls. Different evaluation metrics such as the classification accuracy, F1 score, recall, precision, area under the receiver operating characteristics curve (AUC) are used. Our proposed CO-ResNet obtains consistently best performance in the multi-level data classification problem, including health lung, pneumonia affected lung and COVID-19 affected lung samples. In the experimental evaluation, the detection rate accuracy in discerning COVID-19 is 98.74%, and for healthy normal lungs, pneumonia affected lungs are 92.08% and 91.32% respectively for our CO-ResNet with ResNet101 backbone. Further, our model obtained accuracy values of 83.68% and 82% for healthy normal lungs and pneumonia affected lungs with ResNet152 backbone. Experimental results indicate the potential usage of our new DL driven model for classification of COVID-19 and pneumonia.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"50 1","pages":"71-85"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85596054","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}
Diabetes has become a global health problem, where a proper diagnosis is vital for the life quality of patients. In this article, a genetic algorithm is put forward for designing type-2 fuzzy inference systems to perform Diabetes Classification. We aim at finding parameter values of Type-2 Trapezoidal membership functions and the type of model (Mamdani or Sugeno) with this optimization. To verify the effectiveness of the proposed approach, the PIMA Indian Diabetes dataset is used, and results are compared with type-1 fuzzy systems. Five attributes are used considered as the inputs of the fuzzy inference systems to obtain a Diabetes diagnosis. The instances are divided into design and testing sets, where the design set allows the genetic algorithm to minimize the error of classification, and finally, the real behavior of the fuzzy inference system is validated with the testing set.
{"title":"Optimal design of type-2 fuzzy systems for diabetes classification based on genetic algorithms","authors":"P. Melin, D. Sánchez","doi":"10.3233/HIS-210004","DOIUrl":"https://doi.org/10.3233/HIS-210004","url":null,"abstract":"Diabetes has become a global health problem, where a proper diagnosis is vital for the life quality of patients. In this article, a genetic algorithm is put forward for designing type-2 fuzzy inference systems to perform Diabetes Classification. We aim at finding parameter values of Type-2 Trapezoidal membership functions and the type of model (Mamdani or Sugeno) with this optimization. To verify the effectiveness of the proposed approach, the PIMA Indian Diabetes dataset is used, and results are compared with type-1 fuzzy systems. Five attributes are used considered as the inputs of the fuzzy inference systems to obtain a Diabetes diagnosis. The instances are divided into design and testing sets, where the design set allows the genetic algorithm to minimize the error of classification, and finally, the real behavior of the fuzzy inference system is validated with the testing set.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"33 1","pages":"15-32"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90516014","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}
Conventional surveillance devices are deployed at fixed locations on road sideways, poles or on traffic lights, which provide a constant and fixed surveillance view of the urban traffic. Unmanned aerial vehicles (UAVs) have for last two decades received considerable attention in building smart and effective system with wider coverage using low cost, highly flexible unmanned platform for smart city infrastructure. Unlike fixed monitoring devices, the camera platform of aerial vehicles has many constraints, as it is in constant motion including titling and panning, and thus makes it difficult to process data for real time applications. The inaccuracy in object detection rates from UAV videos has motivated the research community to combine different approaches such as optical flow and supervised learning algorithms. The method proposed in this research incorporates steps that include Kanade-Lucas optical flow method for moving object detection, building connected graphs to isolate objects and convolutional neural network (CNN), followed by support vector machine (SVM) for final classification. The generated optical flow contains background (and tiny) objects detected as vehicle as the camera platform moves. The classifier introduced here rules out the presence of any other (moving) objects to be detected as vehicles. The methodology adopted is tested on a stationary and moving aerial videos. The system is shown to have performance accuracy of 100% in case of stationary video and 98% in case of video from aerial platform.
{"title":"CNN-SVM based vehicle detection for UAV platform","authors":"N. Valappil, Q. Memon","doi":"10.3233/HIS-210003","DOIUrl":"https://doi.org/10.3233/HIS-210003","url":null,"abstract":"Conventional surveillance devices are deployed at fixed locations on road sideways, poles or on traffic lights, which provide a constant and fixed surveillance view of the urban traffic. Unmanned aerial vehicles (UAVs) have for last two decades received considerable attention in building smart and effective system with wider coverage using low cost, highly flexible unmanned platform for smart city infrastructure. Unlike fixed monitoring devices, the camera platform of aerial vehicles has many constraints, as it is in constant motion including titling and panning, and thus makes it difficult to process data for real time applications. The inaccuracy in object detection rates from UAV videos has motivated the research community to combine different approaches such as optical flow and supervised learning algorithms. The method proposed in this research incorporates steps that include Kanade-Lucas optical flow method for moving object detection, building connected graphs to isolate objects and convolutional neural network (CNN), followed by support vector machine (SVM) for final classification. The generated optical flow contains background (and tiny) objects detected as vehicle as the camera platform moves. The classifier introduced here rules out the presence of any other (moving) objects to be detected as vehicles. The methodology adopted is tested on a stationary and moving aerial videos. The system is shown to have performance accuracy of 100% in case of stationary video and 98% in case of video from aerial platform.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"56 1","pages":"59-70"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84514458","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}
The main problem in agriculture is the attack of diseases on the leaves of plants and the spread of agricultural pests. For this reason, we will present how to treat certain phenomena of disease in plants, or how to prevent and do the precautionary measures to adopt a modern method to diagnose the deficiency of the leaves elements of the diseased plants. Thus, the deep learning is the most appropriate solution to detect the properties of the leaves and is essential in the tracking of large fields of crops as well as automatically detecting the symptoms of the leaves characteristics as soon as they appear on the plants leaves. In this paper, we clarified the Transfer Learning (TL) architecture for VGG-16 and the other architecture like ResNet to detect plants that suffer from diseases in the sheet due to a lack of ingredient using a set of increased data based on the leaves of healthy and unhealthy plants alike. The experimental results show that significant detection accuracy improvement has been achieved thanks to our proposed model compared to other reported methods.
{"title":"Diagnostic method based DL approach to detect the lack of elements from the leaves of diseased plants","authors":"M. Elleuch, Fatma Marzougui, M. Kherallah","doi":"10.3233/HIS-210002","DOIUrl":"https://doi.org/10.3233/HIS-210002","url":null,"abstract":"The main problem in agriculture is the attack of diseases on the leaves of plants and the spread of agricultural pests. For this reason, we will present how to treat certain phenomena of disease in plants, or how to prevent and do the precautionary measures to adopt a modern method to diagnose the deficiency of the leaves elements of the diseased plants. Thus, the deep learning is the most appropriate solution to detect the properties of the leaves and is essential in the tracking of large fields of crops as well as automatically detecting the symptoms of the leaves characteristics as soon as they appear on the plants leaves. In this paper, we clarified the Transfer Learning (TL) architecture for VGG-16 and the other architecture like ResNet to detect plants that suffer from diseases in the sheet due to a lack of ingredient using a set of increased data based on the leaves of healthy and unhealthy plants alike. The experimental results show that significant detection accuracy improvement has been achieved thanks to our proposed model compared to other reported methods.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"61 1","pages":"33-42"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76048841","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}
With the surge of computational power and efficient energy consumption management on embedded devices, embedded processing has grown exponentially during the last decade. In particular, computer vision has become prevalent in real-time embedded systems, which have always been a victim of transient fault due to its pervasive presence in harsh environments. Convolutional Neural Networks (CNN) are popular in the domain of embedded vision (computer vision in embedded systems) given the success they have shown. One problem encountered is that a pre-trained CNN on embedded devices is vastly affected by Silent Data Corruption (SDC). SDC refers to undetected data corruption that causes errors in data without any indication that the data is incorrect, and thus goes undetected. In this paper, we propose a software-based approach to recover the corrupted bits of a pre-trained CNN due to SDC. Our approach uses a rule-mining algorithm and we conduct experiments on the propagation of error through the topology of the CNN in order to detect the association of the bits for the weights of the pre-trained CNN. This approach increases the robustness of safety-critical embedded vision applications in volatile conditions. A proof of concept has been conducted for a combination of a CNN and a vision data set. We have successfully established the effectiveness of this approach for a very high level of SDC. The proposed approach can further be extended to other networks and data sets.
{"title":"Recovery algorithm to correct silent data corruption of synaptic storage in convolutional neural networks","authors":"A. Roy, Simone A. Ludwig","doi":"10.3233/HIS-200278","DOIUrl":"https://doi.org/10.3233/HIS-200278","url":null,"abstract":"With the surge of computational power and efficient energy consumption management on embedded devices, embedded processing has grown exponentially during the last decade. In particular, computer vision has become prevalent in real-time embedded systems, which have always been a victim of transient fault due to its pervasive presence in harsh environments. Convolutional Neural Networks (CNN) are popular in the domain of embedded vision (computer vision in embedded systems) given the success they have shown. One problem encountered is that a pre-trained CNN on embedded devices is vastly affected by Silent Data Corruption (SDC). SDC refers to undetected data corruption that causes errors in data without any indication that the data is incorrect, and thus goes undetected. In this paper, we propose a software-based approach to recover the corrupted bits of a pre-trained CNN due to SDC. Our approach uses a rule-mining algorithm and we conduct experiments on the propagation of error through the topology of the CNN in order to detect the association of the bits for the weights of the pre-trained CNN. This approach increases the robustness of safety-critical embedded vision applications in volatile conditions. A proof of concept has been conducted for a combination of a CNN and a vision data set. We have successfully established the effectiveness of this approach for a very high level of SDC. The proposed approach can further be extended to other networks and data sets.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"137 1","pages":"177-187"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75920089","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}
While software development productivity has grown rapidly, the weight values assigned to count standard Function Point (FP) created at IBM twenty-five years ago have never been updated. This obsolescence raises critical questions about the validity of the weight values; it also creates other problems such as ambiguous classification, crisp boundary, as well as subjective and locally defined weight values. All of these challenges reveal the need to calibrate FP in order to reflect both the specific software application context and the trend of today's software development techniques more accurately. We have created a FP calibration model that incorporates the learning ability of neural networks as well as the capability of capturing human knowledge using fuzzy logic. The empirical validation using ISBSG Data Repository (release 8) shows an average improvement of 22% in the accuracy of software effort estimations with the new calibration.
{"title":"Updating weight values for function point counting","authors":"Wei Xia, D. Ho, Luiz Fernando Capretz, F. Ahmed","doi":"10.3233/HIS-2009-0061","DOIUrl":"https://doi.org/10.3233/HIS-2009-0061","url":null,"abstract":"While software development productivity has grown rapidly, the weight values assigned to count standard Function Point (FP) created at IBM twenty-five years ago have never been updated. This obsolescence raises critical questions about the validity of the weight values; it also creates other problems such as ambiguous classification, crisp boundary, as well as subjective and locally defined weight values. All of these challenges reveal the need to calibrate FP in order to reflect both the specific software application context and the trend of today's software development techniques more accurately. We have created a FP calibration model that incorporates the learning ability of neural networks as well as the capability of capturing human knowledge using fuzzy logic. The empirical validation using ISBSG Data Repository (release 8) shows an average improvement of 22% in the accuracy of software effort estimations with the new calibration.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"96 1","pages":"1-14"},"PeriodicalIF":0.0,"publicationDate":"2020-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75860672","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}
{"title":"Bagging based ensemble of Support Vector Machines with improved elitist GA-SVM features selection for cardiac arrhythmia classification","authors":"V. J. Kadam, S. Jadhav, Samir S. Yadav","doi":"10.3233/HIS-190276","DOIUrl":"https://doi.org/10.3233/HIS-190276","url":null,"abstract":"","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":"70 1","pages":"25-33"},"PeriodicalIF":0.0,"publicationDate":"2020-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84125586","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：