Current Search: support vector machines (x)
View All Items
(1 - 13 of 13)
- Title
- EVOLUTIONARY OPTIMIZATION OF SUPPORT VECTOR MACHINES.
- Creator
-
Gruber, Fred, Rabelo, Luis, University of Central Florida
- Abstract / Description
-
Support vector machines are a relatively new approach for creating classifiers that have become increasingly popular in the machine learning community. They present several advantages over other methods like neural networks in areas like training speed, convergence, complexity control of the classifier, as well as a stronger mathematical background based on optimization and statistical learning theory. This thesis deals with the problem of model selection with support vector machines, that is...
Show moreSupport vector machines are a relatively new approach for creating classifiers that have become increasingly popular in the machine learning community. They present several advantages over other methods like neural networks in areas like training speed, convergence, complexity control of the classifier, as well as a stronger mathematical background based on optimization and statistical learning theory. This thesis deals with the problem of model selection with support vector machines, that is, the problem of finding the optimal parameters that will improve the performance of the algorithm. It is shown that genetic algorithms provide an effective way to find the optimal parameters for support vector machines. The proposed algorithm is compared with a backpropagation Neural Network in a dataset that represents individual models for electronic commerce.
Show less - Date Issued
- 2004
- Identifier
- CFE0000244, ucf:46251
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000244
- Title
- The Development of Soil Compressibility Prediction Models and Application to Site Settlement.
- Creator
-
Kirts, Scott, Nam, Boo Hyun, Chopra, Manoj, Sallam, Amr, Xanthopoulos, Petros, University of Central Florida
- Abstract / Description
-
The magnitude of the overall settlement depends on several variables such as the Compression Index, Cc, and Recompression Index, Cr, which are determined by a consolidation test; however, the test is time consuming and labor intensive. Correlations have been developed to approximate these compressibility indexes. In this study, a data driven approach has been employed in order to estimate Cc and Cr. Support Vector Machines classification is used to determine the number of distinct models to...
Show moreThe magnitude of the overall settlement depends on several variables such as the Compression Index, Cc, and Recompression Index, Cr, which are determined by a consolidation test; however, the test is time consuming and labor intensive. Correlations have been developed to approximate these compressibility indexes. In this study, a data driven approach has been employed in order to estimate Cc and Cr. Support Vector Machines classification is used to determine the number of distinct models to be developed. The statistical models are built through a forward selection stepwise regression procedure. Ten variables were used, including the moisture content (w), initial void ratio (eo), dry unit weight (?dry), wet unit weight (?wet), automatic hammer SPT blow count (N), overburden stress (?), fines content (-200), liquid limit (LL), plasticity index (PI), and specific gravity (Gs). The results confirm the need for separate models for three out of four soil types, these being Coarse Grained, Fine Grained, and Organic Peat. The models for each classification have varying degrees of accuracy. The correlations were tested through a series of field tests, settlement analysis, and comparison to known site settlement. The first analysis incorporates developed correlations for Cr, and the second utilizes measured Cc and Cr for each soil layer. The predicted settlements from these two analyses were compared to the measured settlement taken in close proximity. Upon conclusion of the analyses, the results indicate that settlement predictions applying a rule of thumb equating Cc to Cr, accounting for elastic settlement, and using a conventional influence zone of settlement, compares more favorably to measured settlement than that of predictions using measured compressibility index(s). Accuracy of settlement predictions is contingent on a thorough field investigation.
Show less - Date Issued
- 2018
- Identifier
- CFE0007208, ucf:52284
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007208
- Title
- Cost-Sensitive Learning-based Methods for Imbalanced Classification Problems with Applications.
- Creator
-
Razzaghi, Talayeh, Xanthopoulos, Petros, Karwowski, Waldemar, Pazour, Jennifer, Mikusinski, Piotr, University of Central Florida
- Abstract / Description
-
Analysis and predictive modeling of massive datasets is an extremely significant problem that arises in many practical applications. The task of predictive modeling becomes even more challenging when data are imperfect or uncertain. The real data are frequently affected by outliers, uncertain labels, and uneven distribution of classes (imbalanced data). Such uncertainties createbias and make predictive modeling an even more difficult task. In the present work, we introduce a cost-sensitive...
Show moreAnalysis and predictive modeling of massive datasets is an extremely significant problem that arises in many practical applications. The task of predictive modeling becomes even more challenging when data are imperfect or uncertain. The real data are frequently affected by outliers, uncertain labels, and uneven distribution of classes (imbalanced data). Such uncertainties createbias and make predictive modeling an even more difficult task. In the present work, we introduce a cost-sensitive learning method (CSL) to deal with the classification of imperfect data. Typically, most traditional approaches for classification demonstrate poor performance in an environment with imperfect data. We propose the use of CSL with Support Vector Machine, which is a well-known data mining algorithm. The results reveal that the proposed algorithm produces more accurate classifiers and is more robust with respect to imperfect data. Furthermore, we explore the best performance measures to tackle imperfect data along with addressing real problems in quality control and business analytics.
Show less - Date Issued
- 2014
- Identifier
- CFE0005542, ucf:50298
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005542
- Title
- Mahalanobis kernel-based support vector data description for detection of large shifts in mean vector.
- Creator
-
Nguyen, Vu, Maboudou, Edgard, Nickerson, David, Schott, James, University of Central Florida
- Abstract / Description
-
Statistical process control (SPC) applies the science of statistics to various process control in order to provide higher-quality products and better services. The K chart is one among the many important tools that SPC offers. Creation of the K chart is based on Support Vector Data Description (SVDD), a popular data classifier method inspired by Support Vector Machine (SVM). As any methods associated with SVM, SVDD benefits from a wide variety of choices of kernel, which determines the...
Show moreStatistical process control (SPC) applies the science of statistics to various process control in order to provide higher-quality products and better services. The K chart is one among the many important tools that SPC offers. Creation of the K chart is based on Support Vector Data Description (SVDD), a popular data classifier method inspired by Support Vector Machine (SVM). As any methods associated with SVM, SVDD benefits from a wide variety of choices of kernel, which determines the effectiveness of the whole model. Among the most popular choices is the Euclidean distance-based Gaussian kernel, which enables SVDD to obtain a flexible data description, thus enhances its overall predictive capability. This thesis explores an even more robust approach by incorporating the Mahalanobis distance-based kernel (hereinafter referred to as Mahalanobis kernel) to SVDD and compare it with SVDD using the traditional Gaussian kernel. Method's sensitivity is benchmarked by Average Run Lengths obtained from multiple Monte Carlo simulations. Data of such simulations are generated from multivariate normal, multivariate Student's (t), and multivariate gamma populations using R, a popular software environment for statistical computing. One case study is also discussed using a real data set received from Halberg Chronobiology Center. Compared to Gaussian kernel, Mahalanobis kernel makes SVDD and thus the K chart significantly more sensitive to shifts in mean vector, and also in covariance matrix.
Show less - Date Issued
- 2015
- Identifier
- CFE0005676, ucf:50170
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005676
- Title
- DECISION THEORY CLASSIFICATION OF HIGH-DIMENSIONAL VECTORS BASED ON SMALL SAMPLES.
- Creator
-
Bradshaw, David, Pensky, Marianna, University of Central Florida
- Abstract / Description
-
In this paper, we review existing classification techniques and suggest an entirely new procedure for the classification of high-dimensional vectors on the basis of a few training samples. The proposed method is based on the Bayesian paradigm and provides posterior probabilities that a new vector belongs to each of the classes, therefore it adapts naturally to any number of classes. Our classification technique is based on a small vector which is related to the projection of the observation...
Show moreIn this paper, we review existing classification techniques and suggest an entirely new procedure for the classification of high-dimensional vectors on the basis of a few training samples. The proposed method is based on the Bayesian paradigm and provides posterior probabilities that a new vector belongs to each of the classes, therefore it adapts naturally to any number of classes. Our classification technique is based on a small vector which is related to the projection of the observation onto the space spanned by the training samples. This is achieved by employing matrix-variate distributions in classification, which is an entirely new idea. In addition, our method mimics time-tested classification techniques based on the assumption of normally distributed samples. By assuming that the samples have a matrix-variate normal distribution, we are able to replace classification on the basis of a large covariance matrix with classification on the basis of a smaller matrix that describes the relationship of sample vectors to each other.
Show less - Date Issued
- 2005
- Identifier
- CFE0000753, ucf:46593
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000753
- Title
- IMPROVING FMRI CLASSIFICATION THROUGH NETWORK DECONVOLUTION.
- Creator
-
Martinek, Jacob, Zhang, Shaojie, University of Central Florida
- Abstract / Description
-
The structure of regional correlation graphs built from fMRI-derived data is frequently used in algorithms to automatically classify brain data. Transformation on the data is performed during pre-processing to remove irrelevant or inaccurate information to ensure that an accurate representation of the subject's resting-state connectivity is attained. Our research suggests and confirms that such pre-processed data still exhibits inherent transitivity, which is expected to obscure the true...
Show moreThe structure of regional correlation graphs built from fMRI-derived data is frequently used in algorithms to automatically classify brain data. Transformation on the data is performed during pre-processing to remove irrelevant or inaccurate information to ensure that an accurate representation of the subject's resting-state connectivity is attained. Our research suggests and confirms that such pre-processed data still exhibits inherent transitivity, which is expected to obscure the true relationships between regions. This obfuscation prevents known solutions from developing an accurate understanding of a subject's functional connectivity. By removing correlative transitivity, connectivity between regions is made more specific and automated classification is expected to improve. The task of utilizing fMRI to automatically diagnose Attention Deficit/Hyperactivity Disorder was posed by the ADHD-200 Consortium in a competition to draw in researchers and new ideas from outside of the neuroimaging discipline. Researchers have since worked with the competition dataset to produce ever-increasing detection rates. Our approach was empirically tested with a known solution to this problem to compare processing of treated and untreated data, and the detection rates were shown to improve in all cases with a weighted average increase of 5.88%.
Show less - Date Issued
- 2015
- Identifier
- CFH0004895, ucf:45410
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004895
- Title
- FEATURE PRUNING FOR ACTION RECOGNITION IN COMPLEX ENVIRONMENT.
- Creator
-
Nagaraja, Adarsh, Tappen, Marshall, University of Central Florida
- Abstract / Description
-
A significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We...
Show moreA significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We introduce a new action database, created from the Weizmann database, that reveals a significant weakness in systems based on popular cuboid descriptors. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning the system or selecting better interest points. Instead, we show that the problem lies at the descriptor level and must be addressed by modifying descriptors.
Show less - Date Issued
- 2011
- Identifier
- CFE0003882, ucf:48721
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0003882
- Title
- Speech Detection using Gammatone Features and One-Class Support Vector Machine.
- Creator
-
Cooper, Douglas, Mikhael, Wasfy, Wahid, Parveen, Behal, Aman, Richie, Samuel, University of Central Florida
- Abstract / Description
-
A network gateway is a mechanism which provides protocol translation and/or validation of network traffic using the metadata contained in network packets. For media applications such as Voice-over-IP, the portion of the packets containing speech data cannot be verified and can provide a means of maliciously transporting code or sensitive data undetected. One solution to this problem is through Voice Activity Detection (VAD). Many VAD's rely on time-domain features and simple thresholds for...
Show moreA network gateway is a mechanism which provides protocol translation and/or validation of network traffic using the metadata contained in network packets. For media applications such as Voice-over-IP, the portion of the packets containing speech data cannot be verified and can provide a means of maliciously transporting code or sensitive data undetected. One solution to this problem is through Voice Activity Detection (VAD). Many VAD's rely on time-domain features and simple thresholds for efficient speech detection however this doesn't say much about the signal being passed. More sophisticated methods employ machine learning algorithms, but train on specific noises intended for a target environment. Validating speech under a variety of unknown conditions must be possible; as well as differentiating between speech and non- speech data embedded within the packets. A real-time speech detection method is proposed that relies only on a clean speech model for detection. Through the use of Gammatone filter bank processing, the Cepstrum and several frequency domain features are used to train a One-Class Support Vector Machine which provides a clean-speech model irrespective of environmental noise. A Wiener filter is used to provide improved operation for harsh noise environments. Greater than 90% detection accuracy is achieved for clean speech with approximately 70% accuracy for SNR as low as 5dB.
Show less - Date Issued
- 2013
- Identifier
- CFE0005091, ucf:50731
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005091
- Title
- EFFICIENT TECHNIQUES FOR RELEVANCE FEEDBACK PROCESSING IN CONTENT-BASED IMAGE RETRIEVAL.
- Creator
-
Liu, Danzhou, Hua, Kien, University of Central Florida
- Abstract / Description
-
In content-based image retrieval (CBIR) systems, there are two general types of search: target search and category search. Unlike queries in traditional database systems, users in most cases cannot specify an ideal query to retrieve the desired results for either target search or category search in multimedia database systems, and have to rely on iterative feedback to refine their query. Efficient evaluation of such iterative queries can be a challenge, especially when the multimedia database...
Show moreIn content-based image retrieval (CBIR) systems, there are two general types of search: target search and category search. Unlike queries in traditional database systems, users in most cases cannot specify an ideal query to retrieve the desired results for either target search or category search in multimedia database systems, and have to rely on iterative feedback to refine their query. Efficient evaluation of such iterative queries can be a challenge, especially when the multimedia database contains a large number of entries, and the search needs many iterations, and when the underlying distance measure is computationally expensive. The overall processing costs, including CPU and disk I/O, are further emphasized if there are numerous concurrent accesses. To address these limitations involved in relevance feedback processing, we propose a generic framework, including a query model, index structures, and query optimization techniques. Specifically, this thesis has five main contributions as follows. The first contribution is an efficient target search technique. We propose four target search methods: naive random scan (NRS), local neighboring movement (LNM), neighboring divide-and-conquer (NDC), and global divide-and-conquer (GDC) methods. All these methods are built around a common strategy: they do not retrieve checked images (i.e., shrink the search space). Furthermore, NDC and GDC exploit Voronoi diagrams to aggressively prune the search space and move towards target images. We theoretically and experimentally prove that the convergence speeds of GDC and NDC are much faster than those of NRS and recent methods. The second contribution is a method to reduce the number of expensive distance computation when answering k-NN queries with non-metric distance measures. We propose an efficient distance mapping function that transfers non-metric measures into metric, and still preserves the original distance orderings. Then existing metric index structures (e.g., M-tree) can be used to reduce the computational cost by exploiting the triangular inequality property. The third contribution is an incremental query processing technique for Support Vector Machines (SVMs). SVMs have been widely used in multimedia retrieval to learn a concept in order to find the best matches. SVMs, however, suffer from the scalability problem associated with larger database sizes. To address this limitation, we propose an efficient query evaluation technique by employing incremental update. The proposed technique also takes advantage of a tuned index structure to efficiently prune irrelevant data. As a result, only a small portion of the data set needs to be accessed for query processing. This index structure also provides an inexpensive means to process the set of candidates to evaluate the final query result. This technique can work with different kernel functions and kernel parameters. The fourth contribution is a method to avoid local optimum traps. Existing CBIR systems, designed around query refinement based on relevance feedback, suffer from local optimum traps that may severely impair the overall retrieval performance. We therefore propose a simulated annealing-based approach to address this important issue. When a stuck-at-a-local-optimum occurs, we employ a neighborhood search technique (i.e., simulated annealing) to continue the search for additional matching images, thus escaping from the local optimum. We also propose an index structure to speed up such neighborhood search. Finally, the fifth contribution is a generic framework to support concurrent accesses. We develop new storage and query processing techniques to exploit sequential access and leverage inter-query concurrency to share computation. Our experimental results, based on the Corel dataset, indicate that the proposed optimization can significantly reduce average response time while achieving better precision and recall, and is scalable to support a large user community. This latter performance characteristic is largely neglected in existing systems making them less suitable for large-scale deployment. With the growing interest in Internet-scale image search applications, our framework offers an effective solution to the scalability problem.
Show less - Date Issued
- 2009
- Identifier
- CFE0002728, ucf:48162
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002728
- Title
- Context-Centric Affect Recognition From Paralinguistic Features of Speech.
- Creator
-
Marpaung, Andreas, Gonzalez, Avelino, DeMara, Ronald, Sukthankar, Gita, Wu, Annie, Lisetti, Christine, University of Central Florida
- Abstract / Description
-
As the field of affect recognition has progressed, many researchers have shifted from having unimodal approaches to multimodal ones. In particular, the trends in paralinguistic speech affect recognition domain have been to integrate other modalities such as facial expression, body posture, gait, and linguistic speech. Our work focuses on integrating contextual knowledge into paralinguistic speech affect recognition. We hypothesize that a framework to recognize affect through paralinguistic...
Show moreAs the field of affect recognition has progressed, many researchers have shifted from having unimodal approaches to multimodal ones. In particular, the trends in paralinguistic speech affect recognition domain have been to integrate other modalities such as facial expression, body posture, gait, and linguistic speech. Our work focuses on integrating contextual knowledge into paralinguistic speech affect recognition. We hypothesize that a framework to recognize affect through paralinguistic features of speech can improve its performance by integrating relevant contextual knowledge. This dissertation describes our research to integrate contextual knowledge into the paralinguistic affect recognition process from acoustic features of speech. We conceived, built, and tested a two-phased system called the Context-Based Paralinguistic Affect Recognition System (CxBPARS). The first phase of this system is context-free and uses the AdaBoost classifier that applies data on the acoustic pitch, jitter, shimmer, Harmonics-to-Noise Ratio (HNR), and the Noise-to-Harmonics Ratio (NHR) to make an initial judgment about the emotion most likely exhibited by the human elicitor. The second phase then adds context modeling to improve upon the context-free classifications from phase I. CxBPARS was inspired by a human subject study performed as part of this work where test subjects were asked to classify an elicitor's emotion strictly from paralinguistic sounds, and then subsequently provided with contextual information to improve their selections. CxBPARS was rigorously tested and found to, at the worst case, improve the success rate from the state-of-the-art's 42% to 53%.
Show less - Date Issued
- 2019
- Identifier
- CFE0007836, ucf:52831
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007836
- Title
- Learning to Grasp Unknown Objects using Weighted Random Forest Algorithm from Selective Image and Point Cloud Feature.
- Creator
-
Iqbal, Md Shahriar, Behal, Aman, Boloni, Ladislau, Haralambous, Michael, University of Central Florida
- Abstract / Description
-
This method demonstrates an approach to determine the best grasping location on an unknown object using Weighted Random Forest Algorithm. It used RGB-D value of an object as input to find a suitable rectangular grasping region as the output. To accomplish this task, it uses a subspace of most important features from a very high dimensional extensive feature space that contains both image and point cloud features. Usage of most important features in the grasping algorithm has enabled the...
Show moreThis method demonstrates an approach to determine the best grasping location on an unknown object using Weighted Random Forest Algorithm. It used RGB-D value of an object as input to find a suitable rectangular grasping region as the output. To accomplish this task, it uses a subspace of most important features from a very high dimensional extensive feature space that contains both image and point cloud features. Usage of most important features in the grasping algorithm has enabled the system to be computationally very fast while preserving maximum information gain. In this approach, the Random Forest operates using optimum parameters e.g. Number of Trees, Number of Features at each node, Information Gain Criteria etc. ensures optimization in learning, with highest possible accuracy in minimum time in an advanced practical setting. The Weighted Random Forest chosen over Support Vector Machine (SVM), Decision Tree and Adaboost for implementation of the grasping system outperforms the stated machine learning algorithms both in training and testing accuracy and other performance estimates. The Grasping System utilizing learning from a score function detects the rectangular grasping region after selecting the top rectangle that has the largest score. The system is implemented and tested in a Baxter Research Robot with Parallel Plate Gripper in action.
Show less - Date Issued
- 2014
- Identifier
- CFE0005509, ucf:50358
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005509
- Title
- Practical Implementations of the Active Set Method for Support Vector Machine Training with Semi-definite Kernels.
- Creator
-
Sentelle, Christopher, Georgiopoulos, Michael, Anagnostopoulos, Georgios, Kasparis, Takis, Stanley, Kenneth, Young, Cynthia, University of Central Florida
- Abstract / Description
-
The Support Vector Machine (SVM) is a popular binary classification model due to its superior generalization performance, relative ease-of-use, and applicability of kernel methods. SVM training entails solving an associated quadratic programming (QP) that presents significant challenges in terms of speed and memory constraints for very large datasets; therefore, research on numerical optimization techniques tailored to SVM training is vast. Slow training times are especially of concern when...
Show moreThe Support Vector Machine (SVM) is a popular binary classification model due to its superior generalization performance, relative ease-of-use, and applicability of kernel methods. SVM training entails solving an associated quadratic programming (QP) that presents significant challenges in terms of speed and memory constraints for very large datasets; therefore, research on numerical optimization techniques tailored to SVM training is vast. Slow training times are especially of concern when one considers that re-training is often necessary at several values of the model's regularization parameter, C, as well as associated kernel parameters.The active set method is suitable for solving SVM problem and is in general ideal when the Hessian is dense and the solution is sparse-the case for the l1-loss SVM formulation. There has recently been renewed interest in the active set method as a technique for exploring the entire SVM regularization path, which has been shown to solve the SVM solution at all points along the regularization path (all values of C) in not much more time than it takes, on average, to perform training at a single value of C with traditional methods. Unfortunately, the majority of active set implementations used for SVM training require positive definite kernels, and those implementations that do allow semi-definite kernels tend to be complex and can exhibit instability and, worse, lack of convergence. This severely limits applicability since it precludes the use of the linear kernel, can be an issue when duplicate data points exist, and doesn't allow use of low-rank kernel approximations to improve tractability for large datasets. The difficulty, in the case of a semi-definite kernel, arises when a particular active set results in a singular KKT matrix (or the equality-constrained problem formed using the active set is semi-definite). Typically this is handled by explicitly detecting the rank of the KKT matrix. Unfortunately, this adds significant complexity to the implementation; and, if care is not taken, numerical instability, or worse, failure to converge can result. This research shows that the singular KKT system can be avoided altogether with simple modifications to the active set method. The result is a practical, easy to implement active set method that does not need to explicitly detect the rank of the KKT matrix nor modify factorization or solution methods based upon the rank. Methods are given for both conventional SVM training as well as for computing the regularization path that are simple and numerically stable. First, an efficient revised simplex method is efficiently implemented for SVM training (SVM-RSQP) with semi-definite kernels and shown to out-perform competing active set implementations for SVM training in terms of training time as well as shown to perform on-par with state-of-the-art SVM training algorithms such as SMO and SVMLight. Next, a new regularization path-following algorithm for semi-definite kernels (Simple SVMPath) is shown to be orders of magnitude faster, more accurate, and significantly less complex than competing methods and does not require the use of external solvers. Theoretical analysis reveals new insights into the nature of the path-following algorithms. Finally, a method is given for computing the approximate regularization path and approximate kernel path using the warm-start capability of the proposed revised simplex method (SVM-RSQP) and shown to provide significant, orders of magnitude, speed-ups relative to the traditional (")grid search(") where re-training is performed at each parameter value. Surprisingly, it also shown that even when the solution for the entire path is not desired, computing the approximate path can be seen as a speed-up mechanism for obtaining the solution at a single value. New insights are given concerning the limiting behaviors of the regularization and kernel path as well as the use of low-rank kernel approximations.
Show less - Date Issued
- 2014
- Identifier
- CFE0005251, ucf:50600
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005251
- Title
- Automatic Detection of Brain Functional Disorder Using Imaging Data.
- Creator
-
Dey, Soumyabrata, Shah, Mubarak, Jha, Sumit, Hu, Haiyan, Weeks, Arthur, Rao, Ravishankar, University of Central Florida
- Abstract / Description
-
Recently, Attention Deficit Hyperactive Disorder (ADHD) is getting a lot of attention mainly for two reasons. First, it is one of the most commonly found childhood behavioral disorders. Around 5-10% of the children all over the world are diagnosed with ADHD. Second, the root cause of the problem is still unknown and therefore no biological measure exists to diagnose ADHD. Instead, doctors need to diagnose it based on the clinical symptoms, such as inattention, impulsivity and hyperactivity,...
Show moreRecently, Attention Deficit Hyperactive Disorder (ADHD) is getting a lot of attention mainly for two reasons. First, it is one of the most commonly found childhood behavioral disorders. Around 5-10% of the children all over the world are diagnosed with ADHD. Second, the root cause of the problem is still unknown and therefore no biological measure exists to diagnose ADHD. Instead, doctors need to diagnose it based on the clinical symptoms, such as inattention, impulsivity and hyperactivity, which are all subjective.Functional Magnetic Resonance Imaging (fMRI) data has become a popular tool to understand the functioning of the brain such as identifying the brain regions responsible for different cognitive tasks or analyzing the statistical differences of the brain functioning between the diseased and control subjects. ADHD is also being studied using the fMRI data. In this dissertation we aim to solve the problem of automatic diagnosis of the ADHD subjects using their resting state fMRI (rs-fMRI) data.As a core step of our approach, we model the functions of a brain as a connectivity network, which is expected to capture the information about how synchronous different brain regions are in terms of their functional activities. The network is constructed by representing different brain regions as the nodes where any two nodes of the network are connected by an edge if the correlation of the activity patterns of the two nodes is higher than some threshold. The brain regions, represented as the nodes of the network, can be selected at different granularities e.g. single voxels or cluster of functionally homogeneous voxels. The topological differences of the constructed networks of the ADHD and control group of subjects are then exploited in the classification approach.We have developed a simple method employing the Bag-of-Words (BoW) framework for the classification of the ADHD subjects. We represent each node in the network by a 4-D feature vector: node degree and 3-D location. The 4-D vectors of all the network nodes of the training data are then grouped in a number of clusters using K-means; where each such cluster is termed as a word. Finally, each subject is represented by a histogram (bag) of such words. The Support Vector Machine (SVM) classifier is used for the detection of the ADHD subjects using their histogram representation. The method is able to achieve 64% classification accuracy.The above simple approach has several shortcomings. First, there is a loss of spatial information while constructing the histogram because it only counts the occurrences of words ignoring the spatial positions. Second, features from the whole brain are used for classification, but some of the brain regions may not contain any useful information and may only increase the feature dimensions and noise of the system. Third, in our study we used only one network feature, the degree of a node which measures the connectivity of the node, while other complex network features may be useful for solving the proposed problem.In order to address the above shortcomings, we hypothesize that only a subset of the nodes of the network possesses important information for the classification of the ADHD subjects. To identify the important nodes of the network we have developed a novel algorithm. The algorithm generates different random subset of nodes each time extracting the features from a subset to compute the feature vector and perform classification. The subsets are then ranked based on the classification accuracy and the occurrences of each node in the top ranked subsets are measured. Our algorithm selects the highly occurring nodes for the final classification. Furthermore, along with the node degree, we employ three more node features: network cycles, the varying distance degree and the edge weight sum. We concatenate the features of the selected nodes in a fixed order to preserve the relative spatial information. Experimental validation suggests that the use of the features from the nodes selected using our algorithm indeed help to improve the classification accuracy. Also, our finding is in concordance with the existing literature as the brain regions identified by our algorithms are independently found by many other studies on the ADHD. We achieved a classification accuracy of 69.59% using this approach. However, since this method represents each voxel as a node of the network which makes the number of nodes of the network several thousands. As a result, the network construction step becomes computationally very expensive. Another limitation of the approach is that the network features, which are computed for each node of the network, captures only the local structures while ignore the global structure of the network.Next, in order to capture the global structure of the networks, we use the Multi-Dimensional Scaling (MDS) technique to project all the subjects from an unknown network-space to a low dimensional space based on their inter-network distance measures. For the purpose of computing distance between two networks, we represent each node by a set of attributes such as the node degree, the average power, the physical location, the neighbor node degrees, and the average powers of the neighbor nodes. The nodes of the two networks are then mapped in such a way that for all pair of nodes, the sum of the attribute distances, which is the inter-network distance, is minimized. To reduce the network computation cost, we enforce that the maximum relevant information is preserved with minimum redundancy. To achieve this, the nodes of the network are constructed with clusters of highly active voxels while the activity levels of the voxels are measured based on the average power of their corresponding fMRI time-series. Our method shows promise as we achieve impressive classification accuracies (73.55%) on the ADHD-200 data set. Our results also reveal that the detection rates are higher when classification is performed separately on the male and female groups of subjects.So far, we have only used the fMRI data for solving the ADHD diagnosis problem. Finally, we investigated the answers of the following questions. Do the structural brain images contain useful information related to the ADHD diagnosis problem? Can the classification accuracy of the automatic diagnosis system be improved combining the information of the structural and functional brain data? Towards that end, we developed a new method to combine the information of structural and functional brain images in a late fusion framework. For structural data we input the gray matter (GM) brain images to a Convolutional Neural Network (CNN). The output of the CNN is a feature vector per subject which is used to train the SVM classifier. For the functional data we compute the average power of each voxel based on its fMRI time series. The average power of the fMRI time series of a voxel measures the activity level of the voxel. We found significant differences in the voxel power distribution patterns of the ADHD and control groups of subjects. The Local binary pattern (LBP) texture feature is used on the voxel power map to capture these differences. We achieved 74.23% accuracy using GM features, 77.30% using LBP features and 79.14% using combined information.In summary this dissertation demonstrated that the structural and functional brain imaging data are useful for the automatic detection of the ADHD subjects as we achieve impressive classification accuracies on the ADHD-200 data set. Our study also helps to identify the brain regions which are useful for ADHD subject classification. These findings can help in understanding the pathophysiology of the problem. Finally, we expect that our approaches will contribute towards the development of a biological measure for the diagnosis of the ADHD subjects.
Show less - Date Issued
- 2014
- Identifier
- CFE0005786, ucf:50060
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005786
