Artif Intell Med - Vicinal support vector classifier using supervised kernel-based clustering.

Tópicos

{ method(1969) cluster(1462) data(1082) }
{ featur(3375) classif(2383) classifi(1994) }
{ learn(2355) train(1041) set(1003) }
{ problem(2511) optim(1539) algorithm(950) }
{ data(3008) multipl(1320) sourc(1022) }
{ method(1219) similar(1157) match(930) }
{ imag(2830) propos(1344) filter(1198) }
{ chang(1828) time(1643) increas(1301) }
{ concept(1167) ontolog(924) domain(897) }
{ data(1714) softwar(1251) tool(1186) }
{ perform(1367) use(1326) method(1137) }
{ record(1888) medic(1808) patient(1693) }
{ first(2504) two(1366) second(1323) }
{ motion(1329) object(1292) video(1091) }
{ model(3404) distribut(989) bayesian(671) }
{ network(2748) neural(1063) input(814) }
{ perform(999) metric(946) measur(919) }
{ activ(1138) subject(705) human(624) }
{ cancer(2502) breast(956) screen(824) }
{ clinic(1479) use(1117) guidelin(835) }
{ method(1557) propos(1049) approach(1037) }
{ method(984) reconstruct(947) comput(926) }
{ spatial(1525) area(1432) region(1030) }
{ sequenc(1873) structur(1644) protein(1328) }
{ take(945) account(800) differ(722) }
{ assess(1506) score(1403) qualiti(1306) }
{ error(1145) method(1030) estim(1020) }
{ algorithm(1844) comput(1787) effici(935) }
{ model(2220) cell(1177) simul(1124) }
{ featur(1941) imag(1645) propos(1176) }
{ howev(809) still(633) remain(590) }
{ studi(1410) differ(1259) use(1210) }
{ risk(3053) factor(974) diseas(938) }
{ research(1085) discuss(1038) issu(1018) }
{ age(1611) year(1155) adult(843) }
{ medic(1828) order(1363) alert(1069) }
{ signal(2180) analysi(812) frequenc(800) }
{ cost(1906) reduc(1198) effect(832) }
{ group(2977) signific(1463) compar(1072) }
{ sampl(1606) size(1419) use(1276) }
{ use(2086) technolog(871) perceiv(783) }
{ structur(1116) can(940) graph(676) }
{ high(1669) rate(1365) level(1280) }
{ result(1111) use(1088) new(759) }
{ decis(3086) make(1611) patient(1517) }
{ method(2212) result(1239) propos(1039) }
{ can(774) often(719) complex(702) }
{ imag(1947) propos(1133) code(1026) }
{ data(1737) use(1416) pattern(1282) }
{ inform(2794) health(2639) internet(1427) }
{ system(1976) rule(880) can(841) }
{ measur(2081) correl(1212) valu(896) }
{ imag(1057) registr(996) error(939) }
{ bind(1733) structur(1185) ligand(1036) }
{ imag(2675) segment(2577) method(1081) }
{ patient(2315) diseas(1263) diabet(1191) }
{ studi(2440) review(1878) systemat(933) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ framework(1458) process(801) describ(734) }
{ extract(1171) text(1153) clinic(932) }
{ design(1359) user(1324) use(1319) }
{ control(1307) perform(991) simul(935) }
{ care(1570) inform(1187) nurs(1089) }
{ general(901) number(790) one(736) }
{ search(2224) databas(1162) retriev(909) }
{ case(1353) use(1143) diagnosi(1136) }
{ data(3963) clinic(1234) research(1004) }
{ system(1050) medic(1026) inform(1018) }
{ import(1318) role(1303) understand(862) }
{ model(2341) predict(2261) use(1141) }
{ visual(1396) interact(850) tool(830) }
{ compound(1573) activ(1297) structur(1058) }
{ studi(1119) effect(1106) posit(819) }
{ blood(1257) pressur(1144) flow(957) }
{ health(3367) inform(1360) care(1135) }
{ model(3480) simul(1196) paramet(876) }
{ monitor(1329) mobil(1314) devic(1160) }
{ ehr(2073) health(1662) electron(1139) }
{ state(1844) use(1261) util(961) }
{ research(1218) medic(880) student(794) }
{ patient(2837) hospit(1953) medic(668) }
{ model(2656) set(1616) predict(1553) }
{ data(2317) use(1299) case(1017) }
{ gene(2352) biolog(1181) express(1162) }
{ intervent(3218) particip(2042) group(1664) }
{ time(1939) patient(1703) rate(768) }
{ patient(1821) servic(1111) care(1106) }
{ can(981) present(881) function(850) }
{ analysi(2126) use(1163) compon(1037) }
{ health(1844) social(1437) communiti(874) }
{ use(976) code(926) identifi(902) }
{ use(1733) differ(960) four(931) }
{ drug(1928) target(777) effect(648) }
{ implement(1333) system(1263) develop(1122) }
{ survey(1388) particip(1329) question(1065) }
{ estim(2440) model(1874) function(577) }
{ process(1125) use(805) approach(778) }
{ activ(1452) weight(1219) physic(1104) }
{ detect(2391) sensit(1101) algorithm(908) }

Resumo

JECTIVE: Support vector machines (SVMs) have drawn considerable attention due to their high generalisation ability and superior classification performance compared to other pattern recognition algorithms. However, the assumption that the learning data is identically generated from unknown probability distributions may limit the application of SVMs for real problems. In this paper, we propose a vicinal support vector classifier (VSVC) which is shown to be able to effectively handle practical applications where the learning data may originate from different probability distributions.METHODS: The proposed VSVC method utilises a set of new vicinal kernel functions which are constructed based on supervised clustering in the kernel-induced feature space. Our proposed approach comprises two steps. In the clustering step, a supervised kernel-based deterministic annealing (SKDA) clustering algorithm is employed to partition the training data into different soft vicinal areas of the feature space in order to construct the vicinal kernel functions. In the training step, the SVM technique is used to minimise the vicinal risk function under the constraints of the vicinal areas defined in the SKDA clustering step.RESULTS: Experimental results on both artificial and real medical datasets show our proposed VSVC achieves better classification accuracy and lower computational time compared to a standard SVM. For an artificial dataset constructed from non-separated data, the classification accuracy of VSVC is between 95.5% and 96.25% (using different cluster numbers) which compares favourably to the 94.5% achieved by SVM. The VSVC training time is between 8.75s and 17.83s (for 2-8 clusters), considerable less than the 65.0s required by SVM. On a real mammography dataset, the best classification accuracy of VSVC is 85.7% and thus clearly outperforms a standard SVM which obtains an accuracy of only 82.1%. A similar performance improvement is confirmed on two further real datasets, a breast cancer dataset (74.01% vs. 72.52%) and a heart dataset (84.77% vs. 83.81%), coupled with a reduction in terms of learning time (32.07s vs. 92.08s and 25.00s vs. 53.31s, respectively). Furthermore, the VSVC results in the number of support vectors being equal to the specified cluster number, and hence in a much sparser solution compared to a standard SVM.CONCLUSION: Incorporating a supervised clustering algorithm into the SVM technique leads to a sparse but effective solution, while making the proposed VSVC adaptive to different probability distributions of the training data.

Resumo Limpo

jectiv support vector machin svms drawn consider attent due high generalis abil superior classif perform compar pattern recognit algorithm howev assumpt learn data ident generat unknown probabl distribut may limit applic svms real problem paper propos vicin support vector classifi vsvc shown abl effect handl practic applic learn data may origin differ probabl distributionsmethod propos vsvc method utilis set new vicin kernel function construct base supervis cluster kernelinduc featur space propos approach compris two step cluster step supervis kernelbas determinist anneal skda cluster algorithm employ partit train data differ soft vicin area featur space order construct vicin kernel function train step svm techniqu use minimis vicin risk function constraint vicin area defin skda cluster stepresult experiment result artifici real medic dataset show propos vsvc achiev better classif accuraci lower comput time compar standard svm artifici dataset construct nonsepar data classif accuraci vsvc use differ cluster number compar favour achiev svm vsvc train time s s cluster consider less s requir svm real mammographi dataset best classif accuraci vsvc thus clear outperform standard svm obtain accuraci similar perform improv confirm two real dataset breast cancer dataset vs heart dataset vs coupl reduct term learn time s vs s s vs s respect furthermor vsvc result number support vector equal specifi cluster number henc much sparser solut compar standard svmconclus incorpor supervis cluster algorithm svm techniqu lead spars effect solut make propos vsvc adapt differ probabl distribut train data

Resumos Similares

Comput Math Methods Med - Feature selection for better identification of subtypes of Guillain-Barr? syndrome. ( 0,805770012386383 )
Comput Biol Chem - Multi objective SNP selection using pareto optimality. ( 0,780388592857239 )
Comput Methods Programs Biomed - Hepatitis disease diagnosis using a novel hybrid method based on support vector machine and simulated annealing (SVM-SA). ( 0,778777478584002 )
Comput Methods Programs Biomed - Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms. ( 0,754208459263092 )
Comput. Biol. Med. - Predicting cardiac autonomic neuropathy category for diabetic data with missing values. ( 0,737751774075704 )
Neural Comput - Feature selection for ordinal text classification. ( 0,733395769039456 )
IEEE Trans Image Process - Linear discriminant analysis based on L1-norm maximization. ( 0,729284582080221 )
Int J Health Geogr - A binary-based approach for detecting irregularly shaped clusters. ( 0,725495437914136 )
Artif Intell Med - Weighted spherical 1-mean with phase shift and its application in electrocardiogram discord detection. ( 0,724821798096469 )
J. Comput. Biol. - A geometric clustering algorithm with applications to structural data. ( 0,718010947979308 )
Comput Methods Programs Biomed - Classification of intelligence quotient via brainwave sub-band power ratio features and artificial neural network. ( 0,714266272923589 )
Artif Intell Med - A classifier ensemble approach for the missing feature problem. ( 0,707708592921299 )
IEEE Trans Neural Netw Learn Syst - Improved Fault Classification in Series Compensated Transmission Line: Comparative Evaluation of Chebyshev Neural Network Training Algorithms. ( 0,687381883772197 )
IEEE Trans Pattern Anal Mach Intell - Semi-Supervised Kernel Mean Shift Clustering. ( 0,68682669909378 )
J Med Syst - Application of attribute weighting method based on clustering centers to discrimination of linearly non-separable medical datasets. ( 0,684864491470584 )
J Med Syst - A new data preparation method based on clustering algorithms for diagnosis systems of heart and diabetes diseases. ( 0,676905954018673 )
Comput Math Methods Med - Remotely sensed image classification by complex network eigenvalue and connected degree. ( 0,670245556656927 )
Comput. Biol. Med. - Keratin protein property based classification of mammals and non-mammals using machine learning techniques. ( 0,670187075906599 )
Int J Health Geogr - Detecting activity locations from raw GPS data: a novel kernel-based algorithm. ( 0,668259127256043 )
Comput Methods Programs Biomed - An attribute weight assignment and particle swarm optimization algorithm for medical database classifications. ( 0,66652071197222 )
IEEE Trans Pattern Anal Mach Intell - A Link-Based Approach to the Cluster Ensemble Problem. ( 0,664959122444633 )
J Chem Inf Model - Metabolism site prediction based on xenobiotic structural formulas and PASS prediction algorithm. ( 0,664385150244917 )
Comput Methods Programs Biomed - Clustering technique-based least square support vector machine for EEG signal classification. ( 0,66373254306246 )
Int J Health Geogr - Detection of arbitrarily-shaped clusters using a neighbor-expanding approach: a case study on murine typhus in south Texas. ( 0,661646592928468 )
Comput Methods Programs Biomed - Automatic cervical cell segmentation and classification in Pap smears. ( 0,658997406672092 )
J Biomed Inform - Learning Bayesian networks from survival data using weighting censored instances. ( 0,658801916672645 )
Spat Spatiotemporal Epidemiol - Optimal selection of the spatial scan parameters for cluster detection: a simulation study. ( 0,658765505733061 )
Comput. Biol. Med. - On the relevance of automatically selected single-voxel MRS and multimodal MRI and MRSI features for brain tumour differentiation. ( 0,658726971369862 )
J Chem Inf Model - Classifying large chemical data sets: using a regularized potential function method. ( 0,658651951961272 )
AMIA Annu Symp Proc - Using hierarchical mixture of experts model for fusion of outbreak detection methods. ( 0,658433619531667 )
Med Biol Eng Comput - A mathematical method for constraint-based cluster analysis towards optimized constrictive diameter smoothing of saphenous vein grafts. ( 0,657905963394499 )
J Med Syst - Diagnosis of several diseases by using combined kernels with Support Vector Machine. ( 0,657653621571005 )
J Chem Inf Model - Comparison of combinatorial clustering methods on pharmacological data sets represented by machine learning-selected real molecular descriptors. ( 0,652143348838425 )
Comput. Biol. Med. - Sparse Manifold Clustering and Embedding to discriminate gene expression profiles of glioblastoma and meningioma tumors. ( 0,650848428047459 )
J Med Syst - A robust multi-class feature selection strategy based on Rotation Forest Ensemble algorithm for diagnosis of Erythemato-Squamous diseases. ( 0,647418104088269 )
IEEE Trans Image Process - Multiple-kernel, multiple-instance similarity features for efficient visual object detection. ( 0,641811113640448 )
Comput. Biol. Med. - Analysis of adductors angle measurement in Hammersmith infant neurological examinations using mean shift segmentation and feature point based object tracking. ( 0,641166751491444 )
Comput Methods Programs Biomed - Fuzzy and hard clustering analysis for thyroid disease. ( 0,639457917067543 )
Neural Comput - High-dimensional cluster analysis with the masked EM algorithm. ( 0,638718118106584 )
Artif Intell Med - Missing data imputation using statistical and machine learning methods in a real breast cancer problem. ( 0,638402127569807 )
J Biomed Inform - A fast gene selection method for multi-cancer classification using multiple support vector data description. ( 0,636355248418194 )
Artif Intell Med - Automatic detection of epileptic seizures on the intra-cranial electroencephalogram of rats using reservoir computing. ( 0,636309836939017 )
AMIA Annu Symp Proc - Survival prediction and treatment recommendation with Bayesian techniques in lung cancer. ( 0,635165947058571 )
J Am Med Inform Assoc - Privacy-preserving heterogeneous health data sharing. ( 0,630357759289583 )
IEEE Trans Image Process - Efficient image classification via multiple rank regression. ( 0,628833756797222 )
IEEE Trans Vis Comput Graph - GPU-based Multilevel Clustering. ( 0,623492063492063 )
IEEE J Biomed Health Inform - Automatic detection of atrial fibrillation in cardiac vibration signals. ( 0,621078654568322 )
IEEE Trans Image Process - Data-dependent hashing based on p-stable distribution. ( 0,619069097460358 )
IEEE Trans Image Process - Natural image segmentation based on tree equipartition, Bayesian flooding and region merging. ( 0,618094409445401 )
BMC Med Inform Decis Mak - Efficient algorithms for fast integration on large data sets from multiple sources. ( 0,617559876863948 )
Comput. Biol. Med. - A methodology to identify consensus classes from clustering algorithms applied to immunohistochemical data from breast cancer patients. ( 0,617424189343609 )
Neural Comput - Spontaneous clustering via minimum -divergence. ( 0,616002437118495 )
J Chem Inf Model - Investigation of the use of spectral clustering for the analysis of molecular data. ( 0,61571277591961 )
Med Decis Making - Developing appropriate methods for cost-effectiveness analysis of cluster randomized trials. ( 0,611657219788592 )
J Chem Inf Model - Classifying molecules using a sparse probabilistic kernel binary classifier. ( 0,609535492804203 )
Comput Methods Programs Biomed - Comparison of machine learning methods for classifying aphasic and non-aphasic speakers. ( 0,608179630363462 )
J Integr Bioinform - Clustering of gene expression profiles: creating initialization-independent clusterings by eliminating unstable genes. ( 0,606422739828242 )
Artif Intell Med - Multi-test decision tree and its application to microarray data classification. ( 0,603991055236081 )
Comput Methods Programs Biomed - Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering. ( 0,603654235223098 )
Int J Health Geogr - Detection of clusters of a rare disease over a large territory: performance of cluster detection methods. ( 0,603137596774542 )
IEEE J Biomed Health Inform - Identifying Similar Cases in Document Networks using Cross-reference Structures. ( 0,602769034501014 )
IEEE Trans Image Process - Evaluating combinational illumination estimation methods on real-world images. ( 0,602446191220882 )
Comput. Biol. Med. - Genetic fuzzy classifier for sleep stage identification. ( 0,601272492481271 )
J Chem Inf Model - Consensus methods for combining multiple clusterings of chemical structures. ( 0,600906178872965 )
J Integr Bioinform - On the parameter optimization of Support Vector Machines for binary classification. ( 0,600326253966304 )
J Biomed Inform - Average correlation clustering algorithm (ACCA) for grouping of co-regulated genes with similar pattern of variation in their expression values. ( 0,600104364269977 )
IEEE Trans Pattern Anal Mach Intell - A Framework for Automatic Modeling from Pointcloud Data. ( 0,599884739308944 )
Comput Math Methods Med - A wavelet relational fuzzy C-means algorithm for 2D gel image segmentation. ( 0,598344652206859 )
Med Biol Eng Comput - Detection of swallows with silent aspiration using swallowing and breath sound analysis. ( 0,597706577698076 )
Comput Math Methods Med - Correlation kernels for support vector machines classification with applications in cancer data. ( 0,596450285325899 )
J Chem Inf Model - Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. ( 0,592730354683453 )
Comput Math Methods Med - Mixed-norm regularization for brain decoding. ( 0,59044136899968 )
Int J Neural Syst - A genetic graph-based approach for partitional clustering. ( 0,589624577894394 )
J Am Med Inform Assoc - N-gram support vector machines for scalable procedure and diagnosis classification, with applications to clinical free text data from the intensive care unit. ( 0,586542169366798 )
Artif Intell Med - Computer-aided diagnosis of pulmonary nodules using a two-step approach for feature selection and classifier ensemble construction. ( 0,585178935834946 )
Comput Biol Chem - Information-theoretic approaches to SVM feature selection for metagenome read classification. ( 0,584555432606276 )
Comput. Biol. Med. - Computer-aided diagnosis system for the Acute Respiratory Distress Syndrome from chest radiographs. ( 0,583835648898057 )
Int J Neural Syst - Improved adaptive splitting and selection: the hybrid training method of a classifier based on a feature space partitioning. ( 0,583347613679906 )
IEEE Trans Neural Netw Learn Syst - Learning Stable Multilevel Dictionaries for Sparse Representations. ( 0,583116440470906 )
IEEE J Biomed Health Inform - Laryngeal Tumor Detection and Classification in Endoscopic Video. ( 0,58014952150925 )
IEEE Trans Image Process - Joint segmentation of images and scanned point cloud in large-scale street scenes with low-annotation cost. ( 0,580026762198094 )
Comput Methods Programs Biomed - A random forest classifier for lymph diseases. ( 0,578791166317468 )
J Med Syst - Effect of multiscale PCA de-noising on EMG signal classification for diagnosis of neuromuscular disorders. ( 0,578729718470343 )
Comput Biol Chem - A novel divide-and-merge classification for high dimensional datasets. ( 0,57748748355957 )
Comput Methods Programs Biomed - A new hybrid intelligent system for accurate detection of Parkinson's disease. ( 0,577223508879836 )
Med Decis Making - Multiple imputation methods for handling missing data in cost-effectiveness analyses that use data from hierarchical studies: an application to cluster randomized trials. ( 0,576849782321866 )
Comput Math Methods Med - A new particle swarm optimization-based method for phase unwrapping of MRI data. ( 0,575854152994531 )
J Biomed Inform - Quality assessment of data discrimination using self-organizing maps. ( 0,575740839921208 )
J Med Syst - A software framework for building biomedical machine learning classifiers through grid computing resources. ( 0,574632869435792 )
Neural Comput - Large margin low rank tensor analysis. ( 0,574505998974025 )
IEEE Trans Pattern Anal Mach Intell - Time Series Analysis Using Geometric Template Matching. ( 0,573379161051111 )
IEEE Trans Pattern Anal Mach Intell - A Minimum Volume Covering Approach With a Set of Ellipsoids. ( 0,569711927665256 )
Comput. Biol. Med. - Evaluation of automatic feature detection algorithms in EEG: application to interburst intervals. ( 0,568296351042181 )
J Am Med Inform Assoc - Missing values in deduplication of electronic patient data. ( 0,567956139744384 )
Comput Methods Programs Biomed - Improvements on a privacy-protection algorithm for DNA sequences with generalization lattices. ( 0,567202183490519 )
Comput. Biol. Med. - Ant colony optimization-based feature selection method for surface electromyography signals classification. ( 0,56597226064262 )
Comput Methods Programs Biomed - Multiresolution MUAPs decomposition and SVM-based analysis in the classification of neuromuscular disorders. ( 0,565350010358481 )
AMIA Annu Symp Proc - Automatic selection of preprocessing methods for improving predictions on mass spectrometry protein profiles. ( 0,564986757341147 )
Comput Math Methods Med - Decimative spectral estimation with unconstrained model order. ( 0,564875801309809 )
Neural Comput - A nonparametric clustering algorithm with a quantile-based likelihood estimator. ( 0,563198911957567 )