Explore chapters and articles related to this topic
Design and implementation of conflict detection algorithm VHTB
Published in Amir Hussain, Mirjana Ivanovic, Electronics, Communications and Networks IV, 2015
Ying Liu, Fuxiang Gao, Ying Xie
The conflict detection algorithm based on signature refers to Bloom Filter. The read/write set would be mapped to a bit-array. Its length is m. This mapping needs k hash functions. And the bit-array is called a signature (Sanchez 2007). So we can use a finite signature to express an infinite set. It can save a lot of memory space and improve the searching efficiency. Signature has the same advantage as Bloom Filter. It is effective but has some false positives (Zilles 2007). When a false positive happens, one of the concurrent transactions must be aborted. But there is no conflict actually. The false positive rate is an important parameter for system performance. Many conflict detection algorithms based on signature were proposed, such as True Bloom, Hash Bloom and Vertical Hash Bloom. To make good use of the signature, we have studied the advantages of VHB and True Bloom.
Applying AI in Medical Imaging
Published in Lia Morra, Silvia Delsanto, Loredana Correale, Artificial Intelligence in Medical Imaging, 2019
Lia Morra, Silvia Delsanto, Loredana Correale
Once the electronic subtraction of the fecal residue is concluded and the reconstruction and segmentation of the colonic wall has been performed, the CAD system examines voxels of the colonic mucosa to search for polyps. This is typically achieved in two steps: in the first step, i.e. in polyp candidate segmentation, potentially suspicious areas are identified: the goal is to have the highest possible sensitivity. In the second step, the lesion candidates are filtered to reduce the number of false positives presented by the system. Polyp candidate segmentation is typically performed by examining the curvature of the previously segmented colon surface. Polyps can in fact be generally modeled as semi-spheres protruding into the colon lumen. Two curvature features which have been well described in literature for polyp candidate segmentation and classification are shape index and curvedness. These geometrical descriptors may be computed as the first and second order derivatives in intensity level differentiation and express the local shape and the magnitude of the curvature. Shape index and curvedness can quite accurately distinguish polyps from other colonic structures, such as folds, which have a “ridge”-like shape and larger curvature values [205; 203]. Colon surface voxels whose shape index and curvedness are within a predefined range are selected as initial seeds. Voxels are then clustered by spatial density rules to form lesion candidates. One or more classifiers may then be employed to reduce the false positive rate. Four views of a CAD-detected lesion are shown in Figure 3.6.
Algorithmic approaches to BIM modelling from reality
Published in Yusuf Arayici, John Counsell, Lamine Mahdjoubi, Gehan Nagy, Soheir Hawas, Khaled Dewidar, Heritage Building Information Modelling, 2017
Ebenhaeser Joubert, Yusuf Arayici
To solve classification problems, the most commonly used measurement tool is a coincidence matrix. Numbers along the diagonal from top left to bottom right indicate correct outcomes. The numbers in other cells represent errors. The true positive rate or recall is obtained by dividing the correctly classified positives by the total number of positives. The false positive rate is calculated by dividing the incorrectly classified negatives by the total negatives. The overall accuracy of a classifier is calculated by dividing the total number of correctly classified positives and negatives by the total number of samples (Olson and Delen, 2008). Table 12.1 shows a coincidence matrix.
Effective heart disease prediction with Grey-wolf with Firefly algorithm-differential evolution (GF-DE) for feature selection and weighted ANN classification
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2022
The following research gaps are identified from the above related works performed in this study are,Specific optimization models ought to be extended to handle shorter heart-beat signals and long-duration heartbeat signals.The conventional methodologies demand the process of the pre-processing of signals, detections of waveforms, feature-extraction process and the utilization of hand-crafted features for the classification techniques. Hence while in the implementation of these modules, the systems may produce a false-positive rate. This false-positive rate would lead to misdiagnosis process and irrelevant therapies.Some researchers have been justified their proposed model with minimum comparison and thus several effective comparative analysis is required.The processing power consumption of the predictive learning system, the computational time of the implementation would have a dependency on carrying out the feature-selection along with classification models.
Lung nodules detection using grey wolf optimization by weighted filters and classification using CNN
Published in Journal of the Chinese Institute of Engineers, 2022
Anas Bilal, Guangmin Sun, Yu Li, Sarah Mazhar, Jahanzaib Latif
From the results, we saw that the proposed methodology had the following advantages. Improved accuracy reduced the false positive rate.The methodologies adopted previously were based on many noisy, unusable features that might be classified as compromising the results obtained.We included three classes where most of the previous studies only had two classes.
Generative Adversarial Networks Classifier Optimized with Water Strider Algorithm for Fake Tweets Detection
Published in IETE Journal of Research, 2023
V. Muthulakshmi, Francis H. Shajin, J. Dhiviya Rose, P. Rajesh
Abdelminaam et al. [31] have suggested CoAID-DEEP: An Optimized Intelligent Framework for Automated Detecting COVID-19 Misleading Information on Twitter. Here, an updated deep neural network was suggested to fake news detection and also analyzed a large dataset of tweets sending data regarding COVID-19. In the suggested work, the data was classified into 2 groups: fake and non-fake. The results of the suggested method show higher accuracy in detecting fake and non-fake tweets containing COVID-19 information. It provides higher accuracy with a lower false positive rate.