Introduction: Auscultation of heart sounds using digital stethoscope technology is an effective method for the diagnosis of various cardiovascular disorders. The characteristics of phonocardiography (PCG) signals can ...
详细信息
ISBN:
(纸本)9781538645550;9781538666302
Introduction: Auscultation of heart sounds using digital stethoscope technology is an effective method for the diagnosis of various cardiovascular disorders. The characteristics of phonocardiography (PCG) signals can be represented by developing a computer based algorithm as a complementary tool to facilitate clinicians. Aims: This paper aims to address an effective feature extraction and classification technique to improve the detection of two common categories of cardiac arrhythmias, Mitral Valve Prolapse (MVP) and Coronary Artery Disease (CAD) using the heart sound recordings from PhysioNet/Computing in Cardiology 2016 challenge. Methods: Band pass Butterworth filtering is employed to pre-process PCG signals. After detecting heart beats using common segmentation algorithms, beats which are less contaminated by noise are selected using a combination of time and time-frequency analysis. Since heart murmurs are engendered from various abnormalities in the heart, they show different characteristics. To characterize these complexities in each abnormality, Recurrence Quantification Analysis is applied. In this method the Recurrence plots which represent the mechanisms underlying the heart dynamics are quantified into recursive parameters. These set of nonlinear features show a great discrimination between classes. The resulting features are transformed to a new space using Fisher's discriminant analysis (FDA), a dimensionally reduction technique, to reduce the computational complexity of the algorithm. The classification process is in two stage. First, the new dimension-reduced feature vector is the input of the fuzzy C-means clustering (FCM) to predict normal and abnormal class. Then, the obtained 10 dimensional feature vector form RQA analysis feds into a pattern recognition artificial neural network (ANN) to classify CAD and MVP recordings Results: Using PCG signals of CAD, MVP and normal recordings from PhysioNet/Computing in Cardiology 2016, normal signals are eas
The web-based system for online knowledge testing (WbeTS) is a hierarchical and modular autonomous system for remote knowledge assessment whose autonomy is based on remote video surveillance as one of the testing vali...
详细信息
ISBN:
(纸本)9789532330816
The web-based system for online knowledge testing (WbeTS) is a hierarchical and modular autonomous system for remote knowledge assessment whose autonomy is based on remote video surveillance as one of the testing validation mechanisms. The main problem facing the system is the physical implementation of the video surveillance unit for remote monitoring of a student, as well as development of a decision making mechanism based on such monitoring. The monitoring would need to take place in conditions of widely available broadband Internet access and the use of a webcam. A possible solution is a model of the remote control described in this paper, which could solve this problem and make the system more reliable. The model is based on built-in elements and algorithms for visual recognition and motion tracking of the student, sound tracking, user (teacher) interface for assessing the validity of testing and of the system's kernel responsible for assessing the validity of the tests and reporting. The model is envisaged to be implemented accordingly to the wishes and needs of users, and can be integrated as a part of an integral e-learning environment. Although the model described is in principle technologically feasible, its practical realization requires professional refinement and experimental validation. Only by in-depth testing and experiences gained from the actual application of the system will be possible to identify all deficiencies and requirements that currently cannot be predicted.
The performance of anomaly detection algorithms is usually measured using the total residual error. This error metric is calculated by comparing the labels assigned by the detection algorithm against a reference groun...
详细信息
ISBN:
(纸本)9780769551029
The performance of anomaly detection algorithms is usually measured using the total residual error. This error metric is calculated by comparing the labels assigned by the detection algorithm against a reference ground truth. Obtaining a highly expressive ground truth is by itself a challenging task, if not infeasible. Often, a dataset is manually labeled by domain experts. However, manual labeling is error prone. In real-world sensor network deployments, it becomes even more difficult to label a sensor dataset due to the large amount of samples, the complexity of visualizing the data, and the uncertainty in the existence of anomalies. This paper proposes an automated technique which uses highly representative anomaly models for labeling. We demonstrate the effectiveness of this technique through evaluating a classification algorithm using our designed anomaly models as ground truth. We show that the classification accuracy is similar to that when using manually labeled realworld data points.
Hierarchical Multi-label Classification (HMC) is a challenging real-world problem that naturally emerges in several areas. This work proposes two new algorithms using a Probabilistic Graphical Model based on Dependenc...
详细信息
ISBN:
(纸本)9781479945184
Hierarchical Multi-label Classification (HMC) is a challenging real-world problem that naturally emerges in several areas. This work proposes two new algorithms using a Probabilistic Graphical Model based on Dependency Networks (DN) to solve the HMC problem of classifying gene functions into pre-established class hierarchies. DNs are especially attractive for their capability of using traditional, "out-of-the-shelf", classification algorithms to model the relationship among classes and for their ability to cope with cyclic dependencies, resulting in greater flexibility with respect to Bayesian Networks. We tested our two algorithms: the first is a stand-alone Hierarchical Dependency Network (HDN) algorithm, and the second is a hybrid between the HDN and the Predictive Clustering Tree (PCT) algorithm, a well-known classifier for HMC. Based on our experiments, the hybrid classifier, using SVMs as base classifiers, obtained higher predictive accuracy than both the standard PCT algorithm and the HDN algorithm, considering 22 bioinformatics datasets and two out of three predictive accuracy measures specific for hierarchical classification (AU((PRC) over bar) and (AUPRC) over bar (w)).
In this paper, we propose a high performance algorithm for detecting human faces in a still image. Human faces help to communicate and interact in a better way that may be either in human-human interaction or human-ma...
详细信息
ISBN:
(纸本)9781479969449
In this paper, we propose a high performance algorithm for detecting human faces in a still image. Human faces help to communicate and interact in a better way that may be either in human-human interaction or human-machine interaction. The success points for our algorithm is the use of different individual algorithms along with the Unscented Kalman filter (UKF) process, as a novelty of our process. We have modified the algorithms as well. We used Viola Jones eye detector, skin color detector and the Haar cascade classifier for face detection process. Finally, we have conducted a benchmark test for our proposed algorithm using image databases of CMU-MIT, MIT training sets, INRIA Graz-01, and FDDB database. Then, we clarify its effectiveness using ROC curves.
Micro-blogging is a new kind of online broadcast medium rising in latest years which is called weibo in China. Every day, weibo users are fed with a large number of incurious micro-blogs. They may also pay close atten...
详细信息
ISBN:
(纸本)9781479935727
Micro-blogging is a new kind of online broadcast medium rising in latest years which is called weibo in China. Every day, weibo users are fed with a large number of incurious micro-blogs. They may also pay close attention to what celebrities concerned about, but they would rather roughly know the summary of micro-blogs the celebrities, however, they can't add attentions to all the celebrities' friends. In this work, we provide weibo users with an overview of the relevant micro-blogs and offer them a visual summary of the micro-blogs that appeal to famous people. Our goal is to help users select their most interested micro-blogs from a large number of micro-blogs.
ECG lead-wire interchanges involving the right leg (RL) are not always detected. These RL lead-wire interchanges cannot be simulated in the same way as other lead-wire interchanges making database collection a necessi...
详细信息
ISBN:
(纸本)9781538645550;9781538666302
ECG lead-wire interchanges involving the right leg (RL) are not always detected. These RL lead-wire interchanges cannot be simulated in the same way as other lead-wire interchanges making database collection a necessity for algorithm development. Adult 12-lead ECGs from a single teaching hospital taken between January 2008 and July 2012 were reviewed for lead-wire interchanges by an expert electrocardiographer. Lead-wire interchanges were confirmed by comparison of serial ECGs. Positive interchanges included left arm / right leg (flat lead III, n = 134) and right arm / right leg (flat lead II, n = 139). A RL lead-wire interchange algorithm was developed by bootstrap aggregation of decision trees with 5-fold cross validation. Test results were summed over the 5-fold cross validation on the partitions not used for training. ECG features included maximum and minimum QRS and T-wave voltages for ECG leads I, II and III. The Haisty algorithm for RA-RL interchange was tested for comparison. algorithm performance was quantified by sensitivity (SE), specificity (SP) and estimated positive predictive value (PPV) based on SE, SP and realistic prevalence. For a prevalence of 0.2%, performance in SE, SP and PPV was: Haisty, 94, 99.4, 24;tree RA-RL: 84, 99.9, 57;tree LA-RL: 87, 99.9, and 57%. Even though SP was high for all three algorithms, the estimated PPVs were modest due to the low prevalence. Conclusion: Lead-wire interchanges involving the right leg wire can be detected with good sensitivity and high specificity. The higher specificity of the tree based algorithms results in more than twice the PPV of the Haisty algorithm.
We observe that a same ruleset can induce very different memory requirement, as well as varying classification performance, when using various well known decision tree based packet classification algorithms. Worse, tw...
详细信息
ISBN:
(纸本)9781479962044
We observe that a same ruleset can induce very different memory requirement, as well as varying classification performance, when using various well known decision tree based packet classification algorithms. Worse, two similar rulesets, in terms of types and number of rules, can give rise to widely differing performance behaviour for a same classification algorithms. We identify the intrinsic characteristics of rulesets that yield such performance differences, allowing us to understand and predict the performance behaviour of a ruleset for various modern packet classification algorithms. Indeed, from our observations, we are able to derive a memory consumption model and an offline algorithm capable of quickly identifying which packet classification is suited to a give ruleset. By splitting a large ruleset in several subsets and using different packet classification algorithms for different subsets, our SmartSplit algorithm is shown to be capable of configuring a multi-component packet classification system that exhibits up to 11 times less memory consumption, as well as up to about 4x faster classification speed, than the state-of-art work [20] for large rulesets. Our AutoPC framework obtains further performance gain by avoiding splitting large rulesets if the memory size of the built decision tree is shown by the memory consumption model to be small.
Twitter-based messages have presented challenges in the identification of features as applied to classification. This paper explores filtering techniques for improved trend detection and information extraction. Starti...
详细信息
ISBN:
(纸本)9781479940035
Twitter-based messages have presented challenges in the identification of features as applied to classification. This paper explores filtering techniques for improved trend detection and information extraction. Starting with a pre-filtered source (Twitter), we will examine the application of both information theory and Natural Language Processing (NLP) based techniques as a means of preprocessing for classification. Results demonstrate that both means allow for improved results in classification among highly idiosyncratic data (Twitter).
Recently modular multilevel converters are highly attractive for medium, high-voltage power transition and electrical machine drive. Capacitor voltage sorting is very important for capacitor voltage-balancing control....
详细信息
ISBN:
(纸本)9781479914463;9781479914470
Recently modular multilevel converters are highly attractive for medium, high-voltage power transition and electrical machine drive. Capacitor voltage sorting is very important for capacitor voltage-balancing control. This paper describes a novel sorting algorithm for capacitor voltage of modular multilevel converters (MMC).
暂无评论