Classification-based Approaches Research Articles

Identifying hazardousness of sewer pipeline gas mixture using classification methods: a comparative study

In this work, we formulated a real-world problem related to sewer pipeline gas detection using the classification-based approaches. The primary goal of this work was to identify the hazardousness of sewer pipeline to offer safe and non-hazardous access to sewer pipeline workers so that the human fatalities, which occurs due to the toxic exposure of sewer gas components, can be avoided. The dataset acquired through laboratory tests, experiments, and various literature sources was organized to design a predictive model that was able to identify/classify hazardous and non-hazardous situation of sewer pipeline. To design such prediction model, several classification algorithms were used and their performances were evaluated and compared, both empirically and statistically, over the collected dataset. In addition, the performances of several ensemble methods were analyzed to understand the extent of improvement offered by these methods. The result of this comprehensive study showed that the instance-based learning algorithm performed better than many other algorithms such as multilayer perceptron, radial basis function network, support vector machine, reduced pruning tree. Similarly, it was observed that multi-scheme ensemble approach enhanced the performance of base predictors.

Dust storm detection using random forests and physical-based approaches over the Middle East

Dust storms are important phenomena over large regions of the arid and semi-arid areas of the Middle East. Due to the influences of dust aerosols on climate and human daily activities, dust detection plays a crucial role in environmental and climatic studies. Detection of dust storms is critical to accurately understand dust, their properties and distribution. Currently, remotely sensed data such as MODIS (Moderate Resolution Imaging Spectroradiometer) with appropriate temporal and spectral resolutions have been widely used for this purpose. This paper investigates the capability of two physical-based methods, and random forests (RF) classifier, for the first time, to detect dust storms using MODIS imagery. Since the physical-based approaches are empirical, they suffer from certain drawbacks such as high variability of thresholds depending on the underlying surface. Therefore, classification-based approaches could be deployed as an alternative. In this paper, the most relevant bands are chosen based on the physical effects of the major classes, particularly dust, cloud and snow, on both emissive infrared and reflective bands. In order to verify the capability of the methods, OMAERUV AAOD (aerosol absorption optical depth) product from OMI (Ozone Monitoring Instrument) sensor is exploited. In addition, some small regions are selected manually to be considered as ground truth for measuring the probability of false detection (POFD) and probability of missing detection (POMD). The dust class generated by RF is consistent qualitatively with the location and extent of dust observed in OMERAUV and MODIS true colour images. Quantitatively, the dust classes generated for eight dust outbreaks in the Middle East are found to be accurate from 7% and 6% of POFD and POMD respectively. Moreover, results demonstrate the sound capability of RF in classifying dust plumes over both water and land simultaneously. The performance of the physical-based approaches is found weaker than RF due to empirical thresholds that are not always true.

A transversal approach for patch-based label fusion via matrix completion.

Recently, multi-atlas patch-based label fusion has received an increasing interest in the medical image segmentation field. After warping the anatomical labels from the atlas images to the target image by registration, label fusion is the key step to determine the latent label for each target image point. Two popular types of patch-based label fusion approaches are (1) reconstruction-based approaches that compute the target labels as a weighted average of atlas labels, where the weights are derived by reconstructing the target image patch using the atlas image patches; and (2) classification-based approaches that determine the target label as a mapping of the target image patch, where the mapping function is often learned using the atlas image patches and their corresponding labels. Both approaches have their advantages and limitations. In this paper, we propose a novel patch-based label fusion method to combine the above two types of approaches via matrix completion (and hence, we call it transversal). As we will show, our method overcomes the individual limitations of both reconstruction-based and classification-based approaches. Since the labeling confidences may vary across the target image points, we further propose a sequential labeling framework that first labels the highly confident points and then gradually labels more challenging points in an iterative manner, guided by the label information determined in the previous iterations. We demonstrate the performance of our novel label fusion method in segmenting the hippocampus in the ADNI dataset, subcortical and limbic structures in the LONI dataset, and mid-brain structures in the SATA dataset. We achieve more accurate segmentation results than both reconstruction-based and classification-based approaches. Our label fusion method is also ranked 1st in the online SATA Multi-Atlas Segmentation Challenge.

Assessing document and sentence readability in less resourced languages and across textual genres

In this paper, we tackle three underresearched issues of the automatic readability assessment literature, namely the evaluation of text readability in less resourced languages, with respect to sentences (as opposed to documents) as well as across textual genres. Different solutions to these issues have been tested by using and refining READ‑IT, the first advanced readability assessment tool for Italian, which combines traditional raw text features with lexical, morpho-syntactic and syntactic information. In READ‑IT readability assessment is carried out with respect to both documents and sentences, with the latter constituting an important novelty of the proposed approach: READ‑IT shows a high accuracy in the document classification task and promising results in the sentence classification scenario. By comparing the results of two versions of READ‑IT, adopting a classification‑ versus ranking-based approach, we also show that readability assessment is strongly influenced by textual genre; for this reason a genre-oriented notion of readability is needed. With classification-based approaches, reliable results can only be achieved with genre-specific models: Since this is far from being a workable solution, especially for less resourced languages, a new ranking method for readability assessment is proposed, based on the notion of distance.

Treelets Binary Feature Retrieval for Fast Keypoint Recognition.

Fast keypoint recognition is essential to many vision tasks. In contrast to the classification-based approaches, we directly formulate the keypoint recognition as an image patch retrieval problem, which enjoys the merit of finding the matched keypoint and its pose simultaneously. To effectively extract the binary features from each patch surrounding the keypoint, we make use of treelets transform that can group the highly correlated data together and reduce the noise through the local analysis. Treelets is a multiresolution analysis tool, which provides an orthogonal basis to reflect the geometry of the noise-free data. To facilitate the real-world applications, we have proposed two novel approaches. One is the convolutional treelets that capture the image patch information locally and globally while reducing the computational cost. The other is the higher-order treelets that reflect the relationship between the rows and columns within image patch. An efficient sub-signature-based locality sensitive hashing scheme is employed for fast approximate nearest neighbor search in patch retrieval. Experimental evaluations on both synthetic data and the real-world Oxford dataset have shown that our proposed treelets binary feature retrieval methods outperform the state-of-the-art feature descriptors and classification-based approaches.

Cytotoxicity towards CCO cells of imidazolium ionic liquids with functionalized side chains: Preliminary QSTR modeling using regression and classification based approaches

Within this work we evaluated the cytotoxicity towards the Channel Catfish Ovary (CCO) cell line of some imidazolium-based ionic liquids containing different functionalized and unsaturated side chains. The toxic effects were measured by the reduction of the WST-1 dye after 72h exposure resulting in dose- and structure-dependent toxicities. The obtained data on cytotoxic effects of 14 different imidazolium ionic liquids in CCO cells, expressed as EC50 values, were used in a preliminary quantitative structure–toxicity relationship (QSTR) study employing regression- and classification-based approaches. The toxicity of ILs towards CCO was chiefly related to the shape and hydrophobicity parameters of cations. A significant influence of the quantum topological molecular similarity descriptor ellipticity (ε) of the imine bond was also observed.

Video object matching across multiple non-overlapping camera views based on multi-feature fusion and incremental learning

Matching objects across multiple cameras with non-overlapping views is a necessary but difficult task in the wide area video surveillance. Owing to the lack of spatio-temporal information, only the visual information can be used in some scenarios, especially when the cameras are widely separated. This paper proposes a novel framework based on multi-feature fusion and incremental learning to match the objects across disjoint views in the absence of space–time cues. We first develop a competitive major feature histogram fusion representation (CMFH11CMFH is the abbreviation of Competitive Major Feature Histogram fusion representation.) to formulate the appearance model for characterizing the potentially matching objects. The appearances of the objects can change over time and hence the models should be continuously updated. We then adopt an improved incremental general multicategory support vector machine algorithm (IGMSVM22IGMSVM is the abbreviation of Incremental General Multicategory Support Vector Machine learning algorithm.) to update the appearance models online and match the objects based on a classification method. Only a small amount of samples are needed for building an accurate classification model in our method. Several tests are performed on CAVIAR, ISCAPS and VIPeR databases where the objects change significantly due to variations in the viewpoint, illumination and poses. Experimental results demonstrate the advantages of the proposed methodology in terms of computational efficiency, computation storage, and matching accuracy over that of other state-of-the-art classification-based matching approaches. The system developed in this research can be used in real-time video surveillance applications.

Monitoring and Diagnosing Neonatal Seizures by Video Signal Processing

In this thesis we consider the use of well-known statistical methods to early diagnose, through wire-free low-cost video processing, the potential presence of seizures. For this purpose several approaches, have been proposed: periodicity-based, classification-based and clustering-based approaches.

Incorporating the Spine Instability Neoplastic Score into a Treatment Strategy for Spinal Metastasis: LMNOP.

Study Design Review. Objective To describe a decision framework that incorporates key factors to be considered for optimal treatment of spinal metastasis and highlight how this system incorporates the Spinal Instability Neoplastic Score (SINS). Methods We describe how treatment options for spinal metastasis have broadened in recent years with advancements in stereotactic radiosurgery, vertebral augmentation, and other minimally invasive techniques. We discuss classification-based approaches to the treatment of spinal metastasis versus principles-based approaches and argue that the latter may be more appropriate for optimal patient informed consent. Case examples are provided. Results Scoring systems at best produce an estimate of life expectancy but fall short in incorporating all of the relevant factors that determine which treatment(s) may be indicated. We advocate a principle-based decision framework called LMNOP that considers: (L) location of disease with respect to the anterior and/or posterior columns of the spine and number of spinal levels involved (contiguous or non-contiguous); (M) mechanical instability as graded by SINS; (N) neurology (symptomatic epidural spinal cord compression); (O) oncology (histopathologic diagnosis), particularly with respect to radiosensitivity; and (P) patient fitness, patient wishes, prognosis (which is mostly dependent on tumor type), and response to prior therapy. Conclusions LMNOP is the first systematic approach to spinal metastasis that incorporates SINS. It is easy to remember, it addresses clinical factors not directly addressed by other systems, and it is adaptable to changes in technology.

Cascaded multimodal biometric recognition framework

A practically viable multi-biometric recognition system should not only be stable, robust and accurate but should also adhere to real-time processing speed and memory constraints. This study proposes a cascaded classifier-based framework for use in biometric recognition systems. The proposed framework utilises a set of weak classifiers to reduce the enrolled users’ dataset to a small list of candidate users. This list is then used by a strong classifier set as the final stage of the cascade to formulate the decision. At each stage, the candidate list is generated by a Mahalanobis distance-based match score quality measure. One of the key features of the authors framework is that each classifier in the ensemble can be designed to use a different modality thus providing the advantages of a truly multimodal biometric recognition system. In addition, it is one of the first truly multimodal cascaded classifier-based approaches for biometric recognition. The performance of the proposed system is evaluated both for single and multimodalities to demonstrate the effectiveness of the approach.

Pose-Robust Recognition of Low-Resolution Face Images

Face images captured by surveillance cameras usually have poor resolution in addition to uncontrolled poses and illumination conditions, all of which adversely affect the performance of face matching algorithms. In this paper, we develop a completely automatic, novel approach for matching surveillance quality facial images to high-resolution images in frontal pose, which are often available during enrollment. The proposed approach uses multidimensional scaling to simultaneously transform the features from the poor quality probe images and the high-quality gallery images in such a manner that the distances between them approximate the distances had the probe images been captured in the same conditions as the gallery images. Tensor analysis is used for facial landmark localization in the low-resolution uncontrolled probe images for computing the features. Thorough evaluation on the Multi-PIE dataset and comparisons with state-of-the-art super-resolution and classifier-based approaches are performed to illustrate the usefulness of the proposed approach. Experiments on surveillance imagery further signify the applicability of the framework. We also show the usefulness of the proposed approach for the application of tracking and recognition in surveillance videos.

Sparse Conjoint Analysis Through Maximum Likelihood Estimation

Conjoint analysis (CA) is a classical tool used in preference assessment, where the objective is to estimate the utility function of an individual, or a group of individuals, based on expressed preference data. An example is choice-based CA for consumer profiling, i.e., unveiling consumer utility functions based solely on choices between products. A statistical model for choice-based CA is investigated in this paper. Unlike recent classification-based approaches, a sparsity-aware Gaussian maximum likelihood (ML) formulation is proposed to estimate the model parameters. Drawing from related robust parsimonious modeling approaches, the model uses sparsity constraints to account for outliers and to detect the salient features that influence decisions. Contributions include conditions for statistical identifiability, derivation of the pertinent Cramer-Rao Lower Bound (CRLB), and ML consistency conditions for the proposed sparse nonlinear model. The proposed ML approach lends itself naturally to l1-type convex relaxations which are well-suited for distributed implementation, based on the alternating direction method of multipliers (ADMM). A particular decomposition is advocated which bypasses the apparent need for outlier communication, thus maintaining scalability. The performance of the proposed ML approach is demonstrated by comparing against the associated CRLB and prior state-of-the-art using both synthetic and real data sets.

Multidrug Resistance Among New Tuberculosis Cases

Current methodology for multidrug-resistant tuberculosis (MDR TB) surveys endorsed by the World Health Organization provides estimates of MDR TB prevalence among new cases at the national level. On the aggregate, local variation in the burden of MDR TB may be masked. This paper investigates the utility of applying lot quality-assurance sampling to identify geographic heterogeneity in the proportion of new cases with multidrug resistance. We simulated the performance of lot quality-assurance sampling by applying these classification-based approaches to data collected in the most recent TB drug-resistance surveys in Ukraine, Vietnam, and Tanzania. We explored 3 classification systems- two-way static, three-way static, and three-way truncated sequential sampling-at 2 sets of thresholds: low MDR TB = 2%, high MDR TB = 10%, and low MDR TB = 5%, high MDR TB = 20%. The lot quality-assurance sampling systems identified local variability in the prevalence of multidrug resistance in both high-resistance (Ukraine) and low-resistance settings (Vietnam). In Tanzania, prevalence was uniformly low, and the lot quality-assurance sampling approach did not reveal variability. The three-way classification systems provide additional information, but sample sizes may not be obtainable in some settings. New rapid drug-sensitivity testing methods may allow truncated sequential sampling designs and early stopping within static designs, producing even greater efficiency gains. Lot quality-assurance sampling study designs may offer an efficient approach for collecting critical information on local variability in the burden of multidrug-resistant TB. Before this methodology is adopted, programs must determine appropriate classification thresholds, the most useful classification system, and appropriate weighting if unbiased national estimates are also desired.

A Marker-Based Approach for the Automated Selection of a Single Segmentation From a Hierarchical Set of Image Segmentations

The Hierarchical SEGmentation (HSEG) algorithm, which combines region object finding with region object clustering, has given good performances for multi- and hyperspectral image analysis. This technique produces at its output a hierarchical set of image segmentations. The automated selection of a single segmentation level is often necessary. We propose and investigate the use of automatically selected markers for this purpose. In this paper, a novel Marker-based HSEG (M-HSEG) method for spectral-spatial classification of hyperspectral images is proposed. Two classification-based approaches for automatic marker selection are adapted and compared for this purpose. Then, a novel constrained marker-based HSEG algorithm is applied, resulting in a spectral-spatial classification map. Three different implementations of the M-HSEG method are proposed and their performances in terms of classification accuracies are compared. The experimental results, presented for three hyperspectral airborne images, demonstrate that the proposed approach yields accurate segmentation and classification maps, and thus is attractive for remote sensing image analysis.

Adding explicit content classification to nonlinear filters

Nonlinear filters are known for better edge-preserving performance in image processing applications as they can adapt to some local image content. Instead of trying to find a single optimal filter that can adapt to all the image content, some classification-based approaches first apply a pre-classification on the image content and then employ an optimal linear filter for each content class. It is interesting to extend the linear filter in such approaches to a nonlinear filter and see if the explicit content classification, can still add to such inherently adapting nonlinear filters. In this paper, we investigate several categories of nonlinear filters: order statistics filters, hybrid filters, neural filters, and bilateral filters with different forms of content classification in various image processing applications, including image de-blocking, noise reduction, and image interpolation.

An Efficient Tree Classifier Ensemble-Based Approach for Pedestrian Detection

Classification-based pedestrian detection systems (PDSs) are currently a hot research topic in the field of intelligent transportation. A PDS detects pedestrians in real time on moving vehicles. A practical PDS demands not only high detection accuracy but also high detection speed. However, most of the existing classification-based approaches mainly seek for high detection accuracy, while the detection speed is not purposely optimized for practical application. At the same time, the performance, particularly the speed, is primarily tuned based on experiments without theoretical foundations, leading to a long training procedure. This paper starts with measuring and optimizing detection speed, and then a practical classification-based pedestrian detection solution with high detection speed and training speed is described. First, an extended classification/detection speed metric, named feature-per-object (fpo), is proposed to measure the detection speed independently from execution. Then, an fpo minimization model with accuracy constraints is formulated based on a tree classifier ensemble, where the minimum fpo can guarantee the highest detection speed. Finally, the minimization problem is solved efficiently by using nonlinear fitting based on radial basis function neural networks. In addition, the optimal solution is directly used to instruct classifier training; thus, the training speed could be accelerated greatly. Therefore, a rapid and accurate classification-based detection technique is proposed for the PDS. Experimental results on urban traffic videos show that the proposed method has a high detection speed with an acceptable detection rate and a false-alarm rate for onboard detection; moreover, the training procedure is also very fast.

Classification-based approaches to the analysis of functional neuroimaging data on face and object perception

Classification-based approaches to the analysis of functional neuroimaging data on face and object perception

Soft SVM and Its Application in Video-Object Extraction

As a requisite of content-based multimedia technologies, video-object (VO) extraction is a very important yet challenging task. In recent years, classification-based approaches have been proposed to handle VO extraction as a classification problem, for which some promising results have been reported using adaptive neural networks and support vector machines (SVMs). We observe that some training samples in video sequences exhibit partial or ambiguous class memberships, which does not comply with standard membership setups. This problem is addressed in the context of SVM in this paper. By reformulating SVM for the noncrisp classification scenario, we propose a machine which is capable of dealing with binary (or hard) as well as real-valued (or soft) class memberships. The new machine, which is named Soft SVM, is integrated into a VO extraction method, and its effectiveness is demonstrated by the experimental results.

Efficacy of Retrospective Recall of Attention-Deficit Hyperactivity Disorder Symptoms: A Twin Study

Attention-deficit hyperactivity disorder (ADHD) is currently recognized as a neurobiological, genetically based disorder in both children and adults. In this article we examine whether, by using a sample of middle-aged male twin veterans, the phenotypic characterization, prevalence, heritability and the longitudinal course of the illness is comparable to results observed in samples of children and adolescents. We evaluated the utility of adult reports of lifetime ADHD symptoms by examining the heritability of retrospectively reported childhood symptoms, using both symptom-based and discrete classification-based approaches, as well as examining the persistence of ADHD symptoms into adulthood for that subsample of individuals who were judged to possibly have ADHD as children. Our results showed prevalence rates that were approximately similar to those observed in other studies, demonstrable familiality, similar item endorsement patterns, a strong genetic association between hyperactive and inattentive subtypes, and a longitudinal decline in symptom severity. We concluded that while assessing ADHD in adult probands may be less accurate than with children or adolescents, since it demonstrates several characteristics in common with other assessment techniques it remains a viable diagnostic and research strategy, even with population samples.

Classification-Based Spatial Error Concealment for Visual Communications

In an error-prone transmission environment, error concealment is an effective technique to reconstruct the damaged visual content. Due to large variations of image characteristics, different concealment approaches are necessary to accommodate the different nature of the lost image content. In this paper, we address this issue and propose using classification to integrate the state-of-the-art error concealment techniques. The proposed approach takes advantage of multiple concealment algorithms and adaptively selects the suitable algorithm for each damaged image area. With growing awareness that the design of sender and receiver systems should be jointly considered for efficient and reliable multimedia communications, we proposed a set of classification-based block concealment schemes, including receiver-side classification, sender-side attachment, and sender-side embedding. Our experimental results provide extensive performance comparisons and demonstrate that the proposed classification-based error concealment approaches outperform the conventional approaches.