Highest Correct Classification Rate Research Articles

Using focal point learning to improve human–machine tacit coordination

We consider an automated agent that needs to coordinate with a human partner when communication between them is not possible or is undesirable (tacit coordination games). Specifically, we examine situations where an agent and human attempt to coordinate their choices among several alternatives with equivalent utilities. We use machine learning algorithms to help the agent predict human choices in these tacit coordination domains. Experiments have shown that humans are often able to coordinate with one another in communication-free games, by using focal points, prominent solutions to coordination problems. We integrate focal point rules into the machine learning process, by transforming raw domain data into a new hypothesis space. We present extensive empirical results from three different tacit coordination domains. The Focal Point Learning approach results in classifiers with a 40---80% higher correct classification rate, and shorter training time, than when using regular classifiers, and a 35% higher correct classification rate than classical focal point techniques without learning. In addition, the integration of focal points into learning algorithms results in agents that are more robust to changes in the environment. We also present several results describing various biases that might arise in Focal Point based coordination.

Sensitivity Versus Accuracy in Multiclass Problems Using Memetic Pareto Evolutionary Neural Networks

This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high correct classification rate level and a high classification rate for each class. This last objective is not usually optimized in classification, but is considered here given the need to obtain high precision in each class in real problems. To solve this machine learning problem, we use a Pareto-based multiobjective optimization methodology based on a memetic evolutionary algorithm. We consider a memetic Pareto evolutionary approach based on the NSGA2 evolutionary algorithm (MPENSGA2). Once the Pareto front is built, two strategies or automatic individual selection are used: the best model in accuracy and the best model in sensitivity (extremes in the Pareto front). These methodologies are applied to solve 17 classification benchmark problems obtained from the University of California at Irvine (UCI) repository and one complex real classification problem. The models obtained show high accuracy and a high classification rate for each class.

Mother–Calf vocal communication in Atlantic walrus: a first field experimental study

In all colonial pinnipeds studied, mother-young vocal recognition exists and allows rapid and reliable meetings in spite of the confusing environment of the breeding colony. The efficiency of this recognition process guarantees pup survival, especially in species where females alternate foraging sea trips and lactation periods on land. The Atlantic Walrus (Odobenus rosmarus rosmarus) is a highly gregarious pinniped with females attending their calves for an extended period of time (2-3 years). Although we expect mother-calf vocal recognition to occur in this species due to the high density of individuals packed in herds, it has never been experimentally demonstrated. Here, we assessed the individual stereotypy of both mother and calf barks recorded in the wild by measuring frequency and temporal acoustic parameters. Both discriminant function and artificial neural network analyses resulted in high correct classification rates, underlying a well-defined individual stereotypy in parameters related to frequency modulation and frequency values. Playback experiments showed that mothers were more responsive to the barks of their own calf than to those of unrelated young. Finally, propagation experiments revealed that barks propagate at greater distances over water surface than over ice, acoustic features such as frequency modulation and frequency spectrum being highly resistant to degradation during propagation. Thus, acoustic analysis and propagation experiments suggest that these frequency parameters might be the key acoustic features involved in the individual identification process. This experimental study clearly demonstrates that Atlantic walrus has developed a highly reliable mother-calf vocal communication allowing such strong social bond.

Classifying human leg motions with uniaxial piezoelectric gyroscopes.

This paper provides a comparative study on the different techniques of classifying human leg motions that are performed using two low-cost uniaxial piezoelectric gyroscopes worn on the leg. A number of feature sets, extracted from the raw inertial sensor data in different ways, are used in the classification process. The classification techniques implemented and compared in this study are: Bayesian decision making (BDM), a rule-based algorithm (RBA) or decision tree, least-squares method (LSM), k-nearest neighbor algorithm (k-NN), dynamic time warping (DTW), support vector machines (SVM), and artificial neural networks (ANN). A performance comparison of these classification techniques is provided in terms of their correct differentiation rates, confusion matrices, computational cost, and training and storage requirements. Three different cross-validation techniques are employed to validate the classifiers. The results indicate that BDM, in general, results in the highest correct classification rate with relatively small computational cost.

Classification of monofloral honeys from different floral origins and geographical origins based on rheometer

A rheometer was used to classify commercial honeys. Five kinds of Yichun honeys from different floral origins and five kinds of Acacia honeys from different geographical origins were classified based on a rheometer by four pattern recognition techniques: Principal Component Analysis (PCA), Cluster Analysis (CA), Partial Least Squares (PLS), and Support Vector Machines (SVM). All the samples for different floral origins or different geographical origins were demarcated clearly by PCA, PLS. The samples from different floral origins could be classified by SVM, and the samples from different geographical origins also have a high correct classification rate (97.5%). The classification rates for different floral origins and geographical origins were 95% and 97.50% by CA, respectively. Three regression models: Principal Component Regression Analysis (PCR), Partial Least Squares Regression (PLSR), Support Vector Regression (SVR) were used for category forecast. The regression analysis showed that SVR with radial basis function kernel worked most effective.

로버스트추정에 바탕을 둔 주성분로지스틱회귀

로지스틱회귀분석은 고객관계관리를 위한 데이터마이닝 분야에서 많이 사용되는 기법인데, 이 분야의 모형설정 과정에서는 연관성이 매우 높은 설명변수들이 모형에 함께 포함되어 다중공선성의 문제를 유발하며, 더욱이 회귀자료에 이상점들이 포함되면 최우추정량은 심각한 결함을 갖게 된다. 두 가지 문제점을 동시에 해결하기 위하여 로버스트주성분로지스틱회귀를 적용할 수 있는데, 본 논문에서는 주성분의 선정기준을 결정하는 모형을 개발하고, 주성분모형에서의 추정치에 미치는 이상점의 영향을 축소하기 위한 로버스트추정법을 제안하였다. 제안된 추정법은 다중공선성과 이상점이 유발하는 문제들을 적절히 해결해 준다는 사실이 모의실험을 통하여 확인되었다. Logistic regression is widely used as a datamining technique for the customer relationship management. The maximum likelihood estimator has highly inflated variance when multicollinearity exists among the regressors, and it is not robust against outliers. Thus we propose the robust principal components logistic regression to deal with both multicollinearity and outlier problem. A procedure is suggested for the selection of principal components, which is based on the condition index. When a condition index is larger than the cutoff value obtained from the model constructed on the basis of the conjoint analysis, the corresponding principal component is removed from the logistic model. In addition, we employ an algorithm for the robust estimation, which strives to dampen the effect of outliers by applying the appropriate weights and factors to the leverage points and vertical outliers identified by the V-mask type criterion. The Monte Carlo simulation results indicate that the proposed procedure yields higher rate of correct classification than the existing method.

Rotation-invariant texture classification using circular Gabor wavelets

Rotation-invariant texture classification is one of the most challenging problems in computer vision. We present a new and effective method for rotation-invariant texture classification based on circular Gabor wavelets. Two group features can be constructed by the mean and variance of the circular Gabor filtered images and rotation invariants. Using the two group features, a discriminant can be found to classify rotated images. The proposed method is evaluated on three public texture databases: Brodatz, CUReT, and UIUCTex. The experimental results, based on different testing data sets, show that the proposed method has comparatively high correct classification rates not only for the rotated images, but also for the images under different illuminations and viewing directions. The proposed method is robust to additive white noise.

Comparison of Arthroscopy and Arthrotomy for Diagnosis of Medial Meniscal Pathology: An Ex Vivo Study

To evaluate the sensitivity and specificity of arthroscopy and arthrotomy for diagnosis of medial meniscal pathology and to evaluate the diagnostic value of medial meniscal probing. Ex vivo study. Cadaveric canine stifle joints (n=30). Stifle joints were assigned to either a cranial cruciate ligament (CrCL) deficient or intact group. Within each stifle joint, no medial meniscal tear, a peripheral detachment, or 1 of 3 variants of vertical longitudinal tears of the medial meniscus were created. Each stifle joint had arthroscopy, craniomedial (CrMed), and caudomedial (CdMed) arthrotomy. Diagnoses were made by both observation and probing. Sensitivity, specificity, and correct classification rate (CCR) for diagnosing the state of the medial meniscus using both observation and probing with all diagnostic methods were calculated. Odds ratios were calculated to determine if probing increased diagnostic accuracy. Arthroscopy with probing was the most sensitive and specific diagnostic method and had the highest CCR. For arthrotomy, CrMed was the most sensitive in CrCL-deficient and CdMed the most sensitive in stable, CrCL-intact stifle joints. For all methods, probing increased their diagnostic accuracy. Arthroscopy is the most accurate diagnostic method; however, probing the medial meniscus enhances the diagnostic accuracy of all methods. Accurate diagnosis of medial meniscal pathology is ideally achieved by means of arthroscopy; however, if arthrotomy is chosen, CrMed should be selected in unstable and CdMed in stable stifle joints. Regardless, medial meniscal probing should be performed to increase diagnostic accuracy.

Bayesian Learning Using Automatic Relevance Determination Prior with an Application to Earthquake Early Warning

A novel method of Bayesian learning with automatic relevance determination prior is presented that provides a powerful approach to problems of classification based on data features, for example, classifying soil liquefaction potential based on soil and seismic shaking parameters, automatically classifying the damage states of a structure after severe loading based on features of its dynamic response, and real-time classification of earthquakes based on seismic signals. After introduction of the theory, the method is illustrated by applying it to an earthquake record dataset from nine earthquakes to build an efficient real-time algorithm for near-source versus far-source classification of incoming seismic ground motion signals. This classification is needed in the development of early warning systems for large earthquakes. It is shown that the proposed methodology is promising since it provides a classifier with higher correct classification rates and better generalization performance than a previous Bayesian learning method with a fixed prior distribution that was applied to the same classification problem.

Multivariate Analysis of Attenuated Total Reflection—Fourier Transform Infrared Spectroscopic Data to Confirm the Origin of Honeys

Fourier transform infrared (FT-IR) spectroscopy and chemometrics were used to verify the origin of honey samples (n=150) from Europe and South America. Authentic honey samples were collected from five sources, namely unfiltered samples from Mexico in 2004, commercially filtered samples from Ireland and Argentina in 2004, commercially filtered samples from the Czech Republic in 2005 and 2006, and commercially filtered samples from Hungary in 2006. Samples were diluted with distilled water to a standard solids content (70 degrees Brix) and their spectra (2500-12 500 nm) recorded at room temperature using an FT-IR spectrometer equipped with a germanium attenuated total reflection (ATR) accessory. First- and second-derivative and standard normal variate (SNV) data pretreatments were applied to the recorded spectra, which were analyzed using partial least squares (PLS) regression analysis, factorial discriminant analysis (FDA), and soft independent modeling of class analogy (SIMCA). In general, when an attenuated wavelength range (6800-11 500 nm) rather than the whole spectrum (2500-12 500 nm) was studied, higher correct classification rates were achieved. An overall correct classification of 93.3% was obtained for honeys by PLS discriminant analysis, while FDA techniques correctly classified 94.7% of honey samples. Correct classifications of up to 100% were achieved using SIMCA, but models describing some classes had very high false positive rates.

Image statistics and data mining of anal intraepithelial neoplasia

Anal intraepithelial neoplasia (AIN) is a precancerous condition of growing concern, due to the strong interrelation of AIN with infections caused by human papillomaviruses (HPV) and HIV. Several HPV-subtypes induce a variety of tumorous skin lesions and cause different stages of dysplasia and even cancer. The histological classification of AIN is becoming more and more important in clinical practice, due to increasing HPV infection rates throughout human population. Histological slices of anal tissues are commonly classified by individual inspections with all the unavoidable differences of the training status and variances of the individual. Therefore, a quantitative classification method including the calculations of first order as well as second order image statistical parameters in combination with data mining was developed. The results of several classifiers were compared to each other and it turned out that at least two classifiers had very high correct classification rates with very low errors. So it was possible to classify the distinct grades of AIN with high accuracy. The quantitative approach has the potential to minimize individual classification errors significantly and it will enable the establishing of a quantitative screening technique.

A framework for diagnosis of interstitial lung diseases in HRCT: the TALISMAN project

Summary In this paper we describe the goals and the latest outcomes of the TA LISMAN project, the purpose of which is to furnish image-based diagnostic assistance for interstitial lung diseases (ILDs) with secondary data integration. Prototypes of the computer tools are implemented. High correct classification rates of lung tissue regions in high-resolution computed tomography (HRCT), based on a high-quality dataset built from clinical routine, suggests that computerised analysis of HRCT images with integration of the clinical context is ready to be used for computer-aided diagnosis of ILDs. As future tasks, implementation of multimodal retrieval of ILD cases and clinical evaluation of the software are planned to meet clinical needs.

Optimal decision criterion for detecting change in bone mineral density during serial monitoring: A Bayesian approach

Interpretation of change in serial bone densitometry using least significant change (LSC) may not lead to optimal decision making. Using the principles of Bayesian statistics and decision sciences, we developed the Optimal Decision Criterion (ODC) which resulted in 11-12.5% higher rate of correct classification compared with the LSC method. The interpretation of change in serial bone densitometry emphasizes using least significant change (LSC) to distinguish between true changes and measurement error. Using the principles of Bayesian statistics and decision sciences, we developed the optimal decision criterion (ODC) based on maximizing a 'utility' function that rewards the correct and penalizes the incorrect classification of change. The relationship between LSC and ODC is demonstrated using a clinical sample from the Manitoba Bone Density Program. Under certain conditions, it can be shown that using LSC at the 95% confidence level implicitly equates the benefit of 39 true positive diagnoses with the harm of one false positive classification of BMD change. ODC resulted in an 11% higher rate of correct classification for lumbar spine BMD change and a 12.5% better performance for classifying total hip BMD change compared with LSC with this method. ODC has the same clinical interpretation as LSC but with two major advantages: it can incorporate prior knowledge of the likely values of the true change and it can be fine-tuned based on the relative value placed on the correct and incorrect classifications. Bayesian statistics and decision sciences could potentially increase the yield of a BMD monitoring program.

Predicting Recidivism in Probationers With the Youth Level of Service Case Management Inventory (YLS/CMI)

Justice systems depend on risk assessment instruments to identify juveniles who have the greatest likelihood to re-offend. This study was an attempt to validate the Youth Level of Service/Case Management Inventory as a predictor of re-offense for young offenders between the ages of 10 and 16. Although 26% of youth in the sample ( n = 328) re-offended, there were significant differences in offense rates among juveniles classified as high risk, moderate risk, and low risk. The YLS/CMI also had a high correct classification rate, which was reflected in an AUC of .62. Finally, youth of different risk levels also showed differences in time to re-offense rates. Results indicate further study of the YLS/CMI's validity with girls and minorities is necessary. Furthermore, risk prediction could be improved by inclusion of ecological predictive variables related to delinquency.

Identification of SPAM messages using an approach inspired on the immune system

In this paper, an immune-inspired model, named innate and adaptive artificial immune system ( IA-AIS) is proposed and applied to the problem of identification of unsolicited bulk e-mail messages (SPAM). It integrates entities analogous to macrophages, B and T lymphocytes, modeling both the innate and the adaptive immune systems. An implementation of the algorithm was capable of identifying more than 99% of legitimate or SPAM messages in particular parameter configurations. It was compared to an optimized version of the naïve Bayes classifier, which has been attained extremely high correct classification rates. It has been concluded that IA-AIS has a greater ability to identify SPAM messages, although the identification of legitimate messages is not as high as that of the implemented naïve Bayes classifier.

The diagnostic accuracy of power Doppler ultrasonography for differentiating secondary from primary Raynaud’s phenomenon in undifferentiated connective tissue disease

This study was conducted to evaluate the diagnostic accuracy of power Doppler ultrasonography (PDU) for differentiating secondary from primary Raynaud's phenomenon (RP), and also compared PDU with nailfold capillaroscopy (NFC) for the assessment of microvascularity in undifferentiated connective tissue disease (UCTD) patients with RP. Microvascularity in the nailfold and finger tip was evaluated using PDU with cold challenge, and the findings of PDU were classified according to the qualitative grading system before and after cold challenge. NFC was performed at the same day in all persons. The results of PDU were compared with the clinical, laboratory data, and the findings of NFC. The 14 UCTD patients with RP were included in our study. Seven patients were suspected of secondary RP in NFC examination, thus NFC yielded a correct classification into secondary RP in 50% of the UCTD patients. The PDU finding of pattern II, which is regarded as the finding of secondary RP, was observed in 12 UCTD patients with RP. Thus, PDU yielded a correct classification into secondary RP in 86% of UCTD patients. In conclusion, we confirmed that PDU has a higher correct classification rate than NFC for the diagnosing of secondary RP in UCTD patients. Our results suggest that PDU has better accuracy than NFC in differentiating secondary from primary RP, and PDU is more useful in assessing microvascular abnormalities in UCTD patients with RP.

Machine learning methods for microbial source tracking

This paper reports on a successful application of statistical and inductive learning methods to determine optimal discriminating parameters and develop predictive models for the determination of faecal sources in waters, recently and heavily polluted with wastewaters ( microbial source tracking). The data comes from an international study in which various microbial and chemical parameters were determined in heavily polluted waters from diverse geographical areas. A total of 38 variables derived from the microbial and chemical parameters were defined to characterise the available 103 observations. Four methods were evaluated: Euclidean k-nearest-neighbour, linear Bayesian classifier, quadratic Bayesian classifier and a support vector machine. The main aim was the obtention of highly accurate predictive models using the lowest number of variables possible. After a strong feature selection process, the obtained results show that predictive models using only two variables emerge with 100% correct classification. The obtained solutions make use of a linear combination of a discriminating tracer (the enumeration of phages infecting Bacteroides thetaiotaomicron) and a universal non-discriminant faecal indicator. Other models not using the discriminant tracer were developed, though a higher number of variables was needed to achieve a high rate of correct classification.

Assessment of the 16S‐23S rDNA Intergenic Spacer Region in Enterococcus spp. for Microbial Source Tracking

A new library-based microbial source tracking (MST) approach intended for initial application in the coastal waters of Virginia was evaluated. Host-origin isolates of Enterococcus spp. were collected from beaches and the surrounding tidewater region of Virginia and used to construct a library based on the pattern of DNA band lengths produced by the amplification of the 16S-23S rDNA intergenic spacer (IGS) region, and subsequent digestion with MboI. Initial results from small host-origin libraries (64 and 200 total isolates) with discriminant analysis (DA) and logistic regression (LR) yielded high average rates of correct classification (ARCC) for a four-source classification split (birds, dogs, sewage, and wildlife), with ARCCs ranging from 83 to 100%. However, the poor results obtained when classification was attempted on a non-library validation set (VS, ARCCs of 47 and 48%, respectively, using DA and LR) demonstrated that a library of 200 isolates was insufficient to adequately represent the diversity of the enterococci in the sampled region. An increase in the library size to 1029 total isolates was accompanied by a reduction in the ARCC of the library to 42.7% with DA and 45.7% with LR, plus similarly poor results obtained from the VS. The low correct classification rates generated by the larger known-source library were unsuitable for field application. Many reported MST methods have been based on results obtained using small host-origin libraries without external validation. Our results indicate that such an approach can be very misleading, and that larger libraries and external validation is essential for the confirmation of preliminary results.

An efficient quantum neuro-fuzzy classifier based on fuzzy entropy and compensatory operation

In this paper, a quantum neuro-fuzzy classifier (QNFC) for classification applications is proposed. The proposed QNFC model is a five-layer structure, which combines the compensatory-based fuzzy reasoning method with the traditional Takagi---Sugeno---Kang (TSK) fuzzy model. The compensatory-based fuzzy reasoning method uses adaptive fuzzy operations of neuro-fuzzy systems that can make the fuzzy logic system more adaptive and effective. Layer 2 of the QNFC model contains quantum membership functions, which are multilevel activation functions. Each quantum membership function is composed of the sum of sigmoid functions shifted by quantum intervals. A self-constructing learning algorithm, which consists of the self-clustering algorithm (SCA), quantum fuzzy entropy and the backpropagation algorithm, is also proposed. The proposed SCA method is a fast, one-pass algorithm that dynamically estimates the number of clusters in an input data space. Quantum fuzzy entropy is employed to evaluate the information on pattern distribution in the pattern space. With this information, we can determine the number of quantum levels. The backpropagation algorithm is used to tune the adjustable parameters. The simulation results have shown that (1) the QNFC model converges quickly; (2) the QNFC model has a higher correct classification rate than other models.

A neuro-fuzzy technique for fault diagnosis and its application to rotating machinery

Malfunctions in machinery are often sources of reduced productivity and increased maintenance costs in various industrial applications. For this reason, machine condition monitoring is being pursued to recognise incipient faults. In this paper, the fault diagnostic problem is tackled within a neuro-fuzzy approach to pattern classification. Besides the primary purpose of a high rate of correct classification, the proposed neuro-fuzzy approach also aims at obtaining an easily interpretable classification model. The efficiency of the approach is verified with respect to a literature problem and then applied to a case of motor bearing fault classification.